© 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. 222834
    Prev
    Next
    INDEX
    Explanations

    function or state

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

    depending on context

    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
    serde
    0.52
     zijn
    0.50
     steel
    0.48
     النج
    0.47
     scrubbing
    0.46
    로
    0.46
     Steel
    0.46
     steaming
    0.46
    國民
    0.45
     transversal
    0.45
    POSITIVE LOGITS
    MMA
    0.47
    ピンク
    0.45
    cow
    0.44
    annabin
    0.44
    ศี
    0.43
    चंद्र
    0.43
    苜
    0.43
    omach
    0.42
    athlete
    0.42
    ddagger
    0.41
    Activations Density 0.000%

    No Known Activations