© 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. 32893
    Prev
    Next
    INDEX
    Explanations

    and the

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

    text-to-image model

    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
    strcmp
    0.43
    ctomy
    0.43
    assertTrue
    0.42
    밉
    0.42
    lasso
    0.41
    dometer
    0.41
    浿
    0.40
    disconnected
    0.39
     इस्तीफा
    0.39
    detach
    0.38
    POSITIVE LOGITS
    /
    0.48
     genres
    0.47
     variously
    0.44
     каждом
    0.43
     siguientes
    0.43
     restantes
    0.42
     sejumlah
    0.42
    三种
    0.41
     accruing
    0.41
    ilor
    0.41
    Activations Density 0.000%

    No Known Activations