© 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. 67689
    Prev
    Next
    INDEX
    Explanations

    Achieve, Italian, Bavarian, MotoGP

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

    commands and execution

    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
    z
    0.52
    <0x80>
    0.48
    po
    0.48
    ਕ
    0.47
     зна
    0.47
    aj
    0.46
     RULE
    0.46
    no
    0.46
    gn
    0.46
    J
    0.45
    POSITIVE LOGITS
     Achieve
    0.51
     Verizon
    0.48
     Delivered
    0.48
     Italian
    0.45
    极其
    0.45
     Itali
    0.44
     袋
    0.44
     MotoGP
    0.44
     Bavarian
    0.44
     Ended
    0.44
    Activations Density 0.000%

    No Known Activations