© 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. 58423
    Prev
    Next
    INDEX
    Explanations

    lgpl.txt licenses"}, com, models, spectrum

    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
    datac
    -0.68
    心を
    -0.68
     Erlebnis
    -0.68
     Zuhause
    -0.65
     Salah
    -0.64
    bereich
    -0.64
     Deutschland
    -0.64
    EFAULT
    -0.63
     срока
    -0.63
    fell
    -0.62
    POSITIVE LOGITS
     Twit
    0.75
    undan
    0.71
     MED
    0.70
     Kale
    0.69
    issi
    0.68
    ౦
    0.68
     hydroxyl
    0.68
    ָׁ
    0.66
     FAN
    0.66
    Kale
    0.66
    Activations Density 0.065%

    No Known Activations