© 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. 52167
    Prev
    Next
    INDEX
    Explanations

    without compensation or memory module

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

    bones, charts, danger

    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
     dopiero
    0.48
     cannot
    0.47
    怖
    0.44
    ?
    0.43
     Goll
    0.42
     THEN
    0.42
    }
    0.42
     scary
    0.41
     colouring
    0.40
     then
    0.40
    POSITIVE LOGITS
     买
    0.52
    ۹
    0.51
     时间
    0.50
    ssä
    0.50
    팻
    0.50
     Аб
    0.49
    necess
    0.48
     男
    0.47
     （
    0.46
     그는
    0.45
    Activations Density 0.000%

    No Known Activations