© 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. 127721
    Prev
    Next
    INDEX
    Explanations

    off, miss, mom, tuck, regularly

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

    mobilize, distribution, transferring, payments, switch

    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
    ;
    0.46
    assertTrue
    0.45
    Several
    0.45
    Solar
    0.45
    per
    0.45
    are
    0.43
    Glare
    0.43
     Ces
    0.42
     Tailwind
    0.42
    ard
    0.42
    POSITIVE LOGITS
    სახ
    0.50
     तबाद
    0.49
     സമയ
    0.49
     ट्रांसफर
    0.46
    闓
    0.43
    <unused86>
    0.43
     технологі
    0.42
     enl
    0.41
     embezzlement
    0.41
     kapcs
    0.41
    Activations Density 0.000%

    No Known Activations