© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1552
    Prev
    Next
    INDEX
    Explanations

    optic flow and 3D perception

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     forties
    -0.78
     Convers
    -0.76
     decisi
    -0.76
     assisti
    -0.73
    辑
    -0.71
     Goed
    -0.70
    UserInfo
    -0.69
    Specimen
    -0.69
     audi
    -0.68
    Erg
    -0.67
    POSITIVE LOGITS
     Identität
    0.75
    Rpc
    0.75
    /*/
    0.74
    璃
    0.74
     recovering
    0.73
    гів
    0.73
     Nicole
    0.72
    💫
    0.72
     ep
    0.72
    inches
    0.72
    Activations Density 0.078%

    No Known Activations