© 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. 10617
    Prev
    Next
    INDEX
    Explanations

    have surrendered, time will

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

    choice and absence

    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
    request
    0.55
    ל
    0.52
     \
    0.51
    abt
    0.50
     autism
    0.49
    qty
    0.49
    ps
    0.49
    Request
    0.49
    det
    0.49
     supportive
    0.48
    POSITIVE LOGITS
    лась
    0.48
     Paglinawan
    0.48
    ENCED
    0.47
     বাদশা
    0.47
    IamPermissions
    0.46
    ляются
    0.46
    嶋
    0.45
     বহন
    0.45
     Mapa
    0.45
    রোপ
    0.45
    Activations Density 0.000%

    No Known Activations