© 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. 224408
    Prev
    Next
    INDEX
    Explanations

    smaller than, stop damage, effective ways

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

    specific entities and foreign characters

    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
     ampla
    0.52
     ভরে
    0.51
     outras
    0.50
    Ꮶ
    0.50
     abduction
    0.49
     попыта
    0.49
    ⑷
    0.48
     auffi
    0.48
    ルダー
    0.47
     종료
    0.47
    POSITIVE LOGITS
    ០
    0.48
     햇
    0.46
    hen
    0.46
     chariot
    0.42
    Beam
    0.42
     labrador
    0.42
    太陽
    0.42
    kyt
    0.42
     conveyor
    0.42
    ppled
    0.41
    Activations Density 0.000%

    No Known Activations