© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76182
    Prev
    Next
    INDEX
    Explanations

    ionic strength

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects phrases related to ionic strength and concentration in scientific contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The main thing this neuron does is detect numeric tokens that represent quantitative values or measurements.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    这位
    -0.75
    にい
    -0.70
    રી
    -0.70
    jangkau
    -0.67
     Tomar
    -0.64
    yakarta
    -0.64
     baton
    -0.62
    uksessa
    -0.62
     темпера
    -0.62
    ileri
    -0.62
    POSITIVE LOGITS
     strength
    6.88
    strength
    5.84
    Strength
    5.41
     Strength
    5.38
     STRENGTH
    4.25
     strengths
    4.09
    STRENGTH
    3.95
     streng
    3.16
     Strengths
    3.06
     kekuatan
    3.02
    Activations Density 0.046%

    No Known Activations