© 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. 101244
    Prev
    Next
    INDEX
    Explanations

    using the, avoidance, consideration

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

    points, concepts, business, rapping

    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
    es
    0.48
    icure
    0.47
     case
    0.47
     y
    0.46
    s
    0.46
    -
    0.46
    ifold
    0.45
     for
    0.45
     specialization
    0.44
     (
    0.44
    POSITIVE LOGITS
     Когда
    0.54
     Osama
    0.53
     spese
    0.52
    мию
    0.51
    人を
    0.49
     sobreviv
    0.48
    밌
    0.48
     esperti
    0.48
     Gson
    0.47
     मजा
    0.47
    Activations Density 0.000%

    No Known Activations