© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 51573
    Prev
    Next
    INDEX
    Explanations

    medals, sustainability, programming, dental

    np_acts-logits-general · gemini-2.5-flash-lite

    saturation value session

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ه
    0.55
    ہ
    0.50
    an
    0.49
    h
    0.49
    тено
    0.48
    не
    0.47
    gestellt
    0.46
    ди
    0.46
    ص
    0.46
    نف
    0.46
    POSITIVE LOGITS
     razvoja
    0.55
     പറ്റ
    0.52
     lidí
    0.49
     বজায়
    0.49
    Noir
    0.48
     ljudi
    0.47
     ľud
    0.47
     Dealer
    0.46
     granic
    0.46
    Wrapping
    0.46
    Activations Density 0.000%

    No Known Activations