© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 14962
    Prev
    Next
    INDEX
    Explanations

    system files, proper nouns, programming, or non-English

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    dala
    0.46
     lidt
    0.43
    🚈
    0.42
    蜜
    0.41
    不会
    0.41
     苏
    0.40
     KO
    0.40
    不太
    0.38
     jì
    0.38
    ９
    0.38
    POSITIVE LOGITS
    UIT
    0.52
    isio
    0.52
     שלו
    0.48
     ቀን
    0.48
    스코
    0.47
    isna
    0.47
    Brief
    0.45
     scut
    0.45
    ਿਸ
    0.45
    isors
    0.45
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.