© 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. 90545
    Prev
    Next
    INDEX
    Explanations

    constructing a, late Ken

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

    This means

    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
    Image
    0.62
    Vintage
    0.55
    ↵
    0.54
    an
    0.54
    First
    0.54
    Target
    0.54
    Iron
    0.54
    "
    0.54
    France
    0.53
    NI
    0.52
    POSITIVE LOGITS
     güç
    0.56
    ъем
    0.55
     elevationMap
    0.54
     ķ
    0.53
    㕷
    0.52
     αριθ
    0.51
     hài
    0.50
     ampio
    0.50
     hoá
    0.49
     съем
    0.48
    Activations Density 0.001%

    No Known Activations