© 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. 159072
    Prev
    Next
    INDEX
    Explanations

    alternate embodiments

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

    product, maintaining, Saves

    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
    να
    0.55
    מא
    0.49
    Са
    0.48
     crafty
    0.47
    Т
    0.46
    ட்டும்
    0.46
    Ре
    0.46
    Сер
    0.45
    Л
    0.45
    _
    0.44
    POSITIVE LOGITS
     perju
    0.54
     एग्जामिनेशन
    0.48
     अचानक
    0.47
     biasanya
    0.46
     segera
    0.45
     deterior
    0.45
     Dib
    0.44
     shooting
    0.43
     pulang
    0.42
     hysteria
    0.42
    Activations Density 0.001%

    No Known Activations