© 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. 84834
    Prev
    Next
    INDEX
    Explanations

    Q: or identifier

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

    This neuron fires strongly on the word “for,” especially in the pattern “X is for Y” as used in acrostic‐style definitions.

    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
     our
    -1.37
     we
    -1.09
    刹那
    -1.04
     лука
    -1.02
    providedIn
    -1.02
     just
    -0.97
     slide
    -0.95
     unsere
    -0.94
     pouvez
    -0.93
     for
    -0.92
    POSITIVE LOGITS
    acağına
    1.21
     člověk
    1.00
     terminée
    0.98
     vorhandenen
    0.95
     クロス
    0.94
    なこと
    0.94
     скриншот
    0.93
     endeav
    0.93
     andata
    0.93
    也会
    0.93
    Activations Density 0.000%

    No Known Activations