© 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. 92010
    Prev
    Next
    INDEX
    Explanations

    Falk, Halifax, Belt, chalk, dull

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

    Polish palliative care

    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
    la
    0.98
    a
    0.96
    an
    0.93
    u
    0.92
    一
    0.92
    d
    0.88
    li
    0.84
    lo
    0.84
    es
    0.79
    as
    0.78
    POSITIVE LOGITS
     convenio
    0.64
     contempla
    0.64
     dedica
    0.60
    ográf
    0.60
     trein
    0.59
     trat
    0.59
    ০০০
    0.59
     де
    0.59
     প্রশাসন
    0.57
    де
    0.57
    Activations Density 2.529%

    No Known Activations