© 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. 138293
    Prev
    Next
    INDEX
    Explanations

    local businesses

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

    electronics and components

    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
     Shrewsbury
    0.45
    ⬇
    0.42
    <unused63>
    0.42
    _____
    0.42
    ☝
    0.41
    bower
    0.41
    pos
    0.40
    ;?>
    0.40
    하거나
    0.40
    вре
    0.39
    POSITIVE LOGITS
     echte
    0.55
     elektron
    0.49
     echt
    0.48
     uiteindelijk
    0.48
     gebru
    0.48
     elektrische
    0.48
    株式
    0.48
     elektry
    0.46
     ficaram
    0.46
    企業の
    0.46
    Activations Density 0.000%

    No Known Activations