© 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. 31041
    Prev
    Next
    INDEX
    Explanations

    product edit order view

    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
    шні
    -0.87
    TheGreat
    -0.82
    话题
    -0.76
    звание
    -0.75
     required
    -0.75
     NJ
    -0.74
     Sit
    -0.74
     PA
    -0.73
     major
    -0.73
     master
    -0.73
    POSITIVE LOGITS
    nott
    0.91
     источники
    0.91
     misterio
    0.89
     Toshiba
    0.82
     добрый
    0.82
     carcasses
    0.81
    LogFactory
    0.79
    سری
    0.79
    っしゃ
    0.79
    BUG
    0.78
    Activations Density 0.026%

    No Known Activations