© 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. 241847
    Prev
    Next
    INDEX
    Explanations

    specifically for

    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
    Ef
    0.49
     Ef
    0.48
    LA
    0.44
    clockwise
    0.44
    EST
    0.43
     Saf
    0.43
    撾
    0.43
     "?
    0.43
    -'
    0.43
     Shalom
    0.43
    POSITIVE LOGITS
    <0x80>
    0.57
    <0x94>
    0.50
    ボリューム
    0.49
     wyra
    0.48
    otras
    0.47
     tỷ
    0.46
    izado
    0.46
    textrm
    0.46
    ющейся
    0.45
     perek
    0.45
    Activations Density 0.000%

    No Known Activations