© 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. 69151
    Prev
    Next
    INDEX
    Explanations

    doing things yourself

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

    The neuron consistently lights up on the tokens making up subordinate/explanatory clauses (e.g. the “who … that …” and “which … that …” phrases).

    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
     “
    -0.94
     verschiedener
    -0.88
     using
    -0.84
    énage
    -0.82
    मर
    -0.79
    使う
    -0.79
    탕
    -0.79
    giers
    -0.78
     daß
    -0.77
    astă
    -0.77
    POSITIVE LOGITS
     yourself
    1.07
     самостоятельно
    1.05
     phénom
    1.03
     échanti
    1.00
     zelf
    0.98
     başına
    0.98
    blij
    0.94
     sendiri
    0.94
     légiti
    0.93
    genomen
    0.92
    Activations Density 0.053%

    No Known Activations