© 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. 139182
    Prev
    Next
    INDEX
    Explanations

    directors or maker

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

    latest stable versions

    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
    Т
    0.48
     atacar
    0.46
    Р
    0.45
    انية
    0.44
    انوي
    0.44
    ENT
    0.44
    АТО
    0.44
    ATO
    0.44
    HASH
    0.44
     ocupar
    0.44
    POSITIVE LOGITS
    MSFontService
    0.52
     κι
    0.52
    েরও
    0.50
     फेवरेट
    0.50
    ure
    0.49
    nhold
    0.48
    帮你
    0.48
    !</
    0.48
    歳の
    0.48
     שלך
    0.47
    Activations Density 0.001%

    No Known Activations