© 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. 84238
    Prev
    Next
    INDEX
    Explanations

    names of people and things

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    With
    -2.56
    These
    -2.17
    When
    -2.09
    Those
    -2.09
    Without
    -2.08
    Some
    -2.08
    This
    -2.08
    Several
    -2.06
    Although
    -2.03
    Despite
    -2.03
    POSITIVE LOGITS
     trám
    1.61
    ピッタリ
    1.49
    へ向
    1.46
    を終
    1.43
    の方に
    1.42
     horarios
    1.41
    )=>{
    1.38
    の準備
    1.37
    Pisces
    1.37
    が終わ
    1.36
    Activations Density 0.000%

    No Known Activations