© 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. 163149
    Prev
    Next
    INDEX
    Explanations

    introduced several, Devil Deals, election last, fortune making

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

    after creature, monkey

    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
    툴
    0.46
    <mask>
    0.44
    ordinator
    0.44
    రుపు
    0.43
     preventative
    0.43
    阁
    0.43
    espec
    0.42
     lainnya
    0.41
    hesis
    0.40
    ⁂
    0.40
    POSITIVE LOGITS
     pabbaj
    0.60
     ciała
    0.55
     الحصول
    0.53
    cante
    0.52
    ICK
    0.50
     сі
    0.48
     Waalaikumsalam
    0.48
     passports
    0.48
    payments
    0.48
     gacchati
    0.48
    Activations Density 0.000%

    No Known Activations