© 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. 236099
    Prev
    Next
    INDEX
    Explanations

    directed for, providers that, vehicle compatibility

    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
    countries
    0.54
     countries
    0.53
     мест
    0.53
     autori
    0.52
     şehir
    0.52
    <unused325>
    0.50
     最後
    0.50
    <unused2051>
    0.50
    <unused722>
    0.49
    <unused1032>
    0.49
    POSITIVE LOGITS
    วี
    0.45
    뛸
    0.43
     evoking
    0.43
    Proofs
    0.42
    Indigo
    0.41
    과의
    0.39
     exploiting
    0.39
    Jersey
    0.39
     melon
    0.38
     totaling
    0.38
    Activations Density 0.001%

    No Known Activations