© 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. 10-GEMMASCOPE-RES-131K
    7. 13457
    Prev
    Next
    INDEX
    Explanations

    name, email, address, phone

    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_10/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
     "
    -1.72
     }^{*}
    -1.68
    ных
    -1.67
    etsk
    -1.57
    ."
    -1.55
     If
    -1.55
     We
    -1.52
    ">—
    -1.48
     br
    -1.44
    もの
    -1.44
    POSITIVE LOGITS
     about
    2.31
     that
    1.83
     how
    1.74
    伱
    1.70
     for
    1.65
     their
    1.61
     SolutionA
    1.60
     kılıf
    1.55
    اتور
    1.52
     which
    1.51
    Activations Density 0.104%

    No Known Activations