© 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. 79138
    Prev
    Next
    INDEX
    Explanations

    questions asked, format version, link rel

    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
    otech
    -0.79
     mode
    -0.68
     Tec
    -0.67
    illan
    -0.65
    勝手に
    -0.65
    active
    -0.64
     top
    -0.64
     critical
    -0.64
    getConfig
    -0.63
     oncoming
    -0.63
    POSITIVE LOGITS
    enterprise
    0.70
    worpen
    0.67
     photographe
    0.66
    cowboy
    0.65
     Doppel
    0.65
    waves
    0.64
     collecte
    0.63
    سل
    0.63
    idades
    0.62
     Amour
    0.61
    Activations Density 0.071%

    No Known Activations