© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 12137
    Prev
    Next
    INDEX
    Explanations

    project names and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Someone
    0.39
     porcent
    0.39
    ∓
    0.37
    ంచరీలు
    0.37
     alguna
    0.37
     någon
    0.37
     professor
    0.37
     தெரி
    0.36
    Emojis
    0.36
     vytvá
    0.36
    POSITIVE LOGITS
     P
    0.51
     Untitled
    0.51
    _
    0.50
    my
    0.49
    G
    0.49
    mu
    0.49
    untitled
    0.49
     G
    0.49
     FY
    0.48
     MAIN
    0.48
    Activations Density 0.027%

    No Known Activations