© 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. 22-GEMMASCOPE-RES-131K
    7. 27936
    Prev
    Next
    INDEX
    Explanations

    physical appearance, predict tsunami, approach, summary, statements, mention, physical training, later development, toxic

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

    The neuron flags words and phrases that relate to assessing, estimating, or predicting measurable states (e.g. impairment, physical appearance, predict, accurate).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     but
    -1.60
    Vorlage
    -1.16
     of
    -1.11
    )
    -1.08
    єте
    -1.07
    Dichloroprop
    -1.05
     In
    -1.05
     You
    -1.02
     CURLOPT
    -0.98
     At
    -0.98
    POSITIVE LOGITS
     både
    1.70
     sowohl
    1.62
    ต่างๆ
    1.55
     zowel
    1.46
    无论是
    1.40
     variously
    1.33
     allerlei
    1.25
    不仅
    1.24
     either
    1.23
     everything
    1.21
    Activations Density 0.103%

    No Known Activations