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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3400
    Prev
    Next
    INDEX
    Explanations

    facts and conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    e
    2.30
    ה
    2.21
    er
    2.14
    ۰۰
    2.01
    ه
    1.96
    a
    1.95
    ر
    1.89
    ेला
    1.87
    queline
    1.86
    aad
    1.84
    POSITIVE LOGITS
    发挥
    1.76
    ছিলেন
    1.71
     괜찮
    1.67
     khấu
    1.59
    鸯
    1.56
     tỏ
    1.53
     FIXME
    1.53
    骜
    1.50
    库存
    1.49
    müş
    1.48
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.