© 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. 157951
    Prev
    Next
    INDEX
    Explanations

    clear and understandable

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

    clearer code and explanations

    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
     as
    0.79
     -,
    0.79
     tweaking
    0.78
     (
    0.75
     (~
    0.70
     (>
    0.70
    ”,
    0.69
     –,
    0.69
     “,
    0.69
    k
    0.67
    POSITIVE LOGITS
    Clear
    1.37
     clear
    1.20
    clear
    1.19
    CLEAR
    1.16
    清
    1.15
     Clear
    1.13
     क्लियर
    1.10
    清晰
    1.09
    クリア
    1.06
     clears
    1.02
    Activations Density 0.062%

    No Known Activations