© 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. 84621
    Prev
    Next
    INDEX
    Explanations

    qualities and opinions

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

    consequentialism, assessment, flight system

    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
     structural
    0.49
    をお
    0.48
    リ
    0.48
    е
    0.48
    ᅡ
    0.47
    を
    0.47
    inizio
    0.46
    ā
    0.46
    ­
    0.45
     Structural
    0.44
    POSITIVE LOGITS
    ScienceStudent
    0.46
     jeżeli
    0.45
     tarses
    0.44
     observaciones
    0.43
     renseignements
    0.41
     ncols
    0.41
     testes
    0.41
    wenn
    0.41
     évaluations
    0.40
     carène
    0.40
    Activations Density 0.003%

    No Known Activations