© 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. 64630
    Prev
    Next
    INDEX
    Explanations

    `double` types

    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
     فريبيس
    -0.84
     Fremont
    -0.72
     derecha
    -0.69
     Ety
    -0.69
     fré
    -0.69
     Anwar
    -0.68
     lú
    -0.67
    ьа
    -0.66
     extré
    -0.66
     krop
    -0.66
    POSITIVE LOGITS
    papers
    0.82
     Use
    0.69
     oldest
    0.66
     unknown
    0.65
     relatively
    0.65
     placed
    0.64
     Him
    0.63
    Sexo
    0.63
     although
    0.63
     Clark
    0.62
    Activations Density 0.066%

    No Known Activations