© 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. 238428
    Prev
    Next
    INDEX
    Explanations

    GroupId, dim, grating, line, born, guarantees

    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
    层的
    0.51
    豆瓣
    0.50
    φων
    0.45
    ঁপ
    0.44
    េច
    0.44
    formin
    0.44
    &)
    0.44
    bbene
    0.43
    可是
    0.43
    mobili
    0.43
    POSITIVE LOGITS
    2
    0.54
    3
    0.47
     pierwsze
    0.47
    4
    0.45
     quatro
    0.45
    <0xCA>
    0.45
     Τ
    0.45
     oversize
    0.44
    VAC
    0.44
     Д
    0.43
    Activations Density 0.003%

    No Known Activations