© 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. 79086
    Prev
    Next
    INDEX
    Explanations

    prevalence and dominance

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

    parameters and formulas

    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
    क्र
    0.47
    instruct
    0.47
    िप
    0.46
    निम्
    0.46
    Instruct
    0.45
    ম্মদ
    0.45
    选
    0.45
    יל
    0.44
    լ
    0.44
    TRAN
    0.43
    POSITIVE LOGITS
     predominance
    0.54
     tunt
    0.52
    ósfera
    0.49
     tofu
    0.48
     supremacy
    0.47
     domínio
    0.47
     tüket
    0.47
     carburetor
    0.46
     trucker
    0.46
     cig
    0.46
    Activations Density 0.001%

    No Known Activations