© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 39362
    Prev
    Next
    INDEX
    Explanations

    appropriate treatment

    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
     pure
    0.47
     retval
    0.45
    ("[
    0.45
     XVIII
    0.43
     beam
    0.42
     number
    0.41
     trophy
    0.41
     region
    0.40
     On
    0.40
     violent
    0.40
    POSITIVE LOGITS
     kaynağından
    0.52
    luft
    0.50
    ยาก
    0.50
    🏦
    0.49
    you
    0.48
    kadang
    0.47
    ओ
    0.47
    𝚢
    0.47
    jų
    0.46
    अभिने
    0.46
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.