© 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. 63716
    Prev
    Next
    INDEX
    Explanations

    symbols and code contexts

    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
    tró
    -0.72
    <0x95>
    -0.70
    vito
    -0.68
    ぐ
    -0.68
     today
    -0.66
    籽
    -0.66
    Bx
    -0.65
     bobby
    -0.65
     Bian
    -0.65
    ágok
    -0.65
    POSITIVE LOGITS
    믹
    0.74
    田村
    0.72
     Patterson
    0.69
    udesta
    0.68
    ശ
    0.68
     ziyaret
    0.67
    anciers
    0.66
     СМИ
    0.66
    arbeiten
    0.65
     futebol
    0.65
    Activations Density 0.047%

    No Known Activations