© 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. 50613
    Prev
    Next
    INDEX
    Explanations

    Belleville and Thursday

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

    comparisons and evaluations

    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
     for
    0.49
     C
    0.49
     O
    0.46
     do
    0.46
     Q
    0.46
     fallacy
    0.46
     hurdle
    0.46
     o
    0.45
     commercials
    0.45
     Fifa
    0.45
    POSITIVE LOGITS
    ább
    0.46
    ЛО
    0.45
    StartZ
    0.45
     найкра
    0.45
    涷
    0.45
     помочь
    0.44
    ДЕ
    0.44
     допомогти
    0.43
     βοη
    0.43
    டனும்
    0.42
    Activations Density 0.000%

    No Known Activations