© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63748
    Prev
    Next
    INDEX
    Explanations

    list of conditions and the following disclaimer

    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
    OWNER
    -0.68
     businesswoman
    -0.68
    ἠ
    -0.67
    dela
    -0.67
     perfekte
    -0.66
    jutnya
    -0.66
    PT
    -0.66
    нымъ
    -0.64
    keterangan
    -0.64
    Sole
    -0.64
    POSITIVE LOGITS
     trust
    0.82
     своя
    0.77
    IPPI
    0.73
     Trust
    0.71
     نز
    0.69
    rait
    0.68
     Kamp
    0.68
     Tweed
    0.65
    Trust
    0.64
     Tyne
    0.63
    Activations Density 0.058%

    No Known Activations