© 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. 204178
    Prev
    Next
    INDEX
    Explanations

    first-of-its-kind popular titles new items crucial selection

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

    necessary evil

    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
     caractéristique
    0.54
     väik
    0.54
    ྥ
    0.54
    निटी
    0.49
     lã
    0.49
     principalTable
    0.48
     lớn
    0.48
     tỷ
    0.46
    omány
    0.46
     vectơ
    0.46
    POSITIVE LOGITS
    ه
    0.51
    ما
    0.50
    為
    0.48
    '
    0.47
     sets
    0.46
    chuk
    0.45
    リ
    0.44
     ensembles
    0.44
    jeli
    0.44
    بي
    0.43
    Activations Density 0.000%

    No Known Activations