© 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. 54146
    Prev
    Next
    INDEX
    Explanations

    Sinai peninsula

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

    honoring, online communities, signals

    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
     &
    0.50
     sets
    0.50
    PA
    0.48
     G
    0.48
     Lawyer
    0.47
     Re
    0.46
     Barker
    0.46
    al
    0.46
    alat
    0.45
    hore
    0.45
    POSITIVE LOGITS
    考え
    0.50
    테
    0.50
    𝘧
    0.49
    θούν
    0.49
    ruzione
    0.49
    シーズン
    0.48
    ਡ
    0.48
    トゥーン
    0.47
    万円
    0.47
    ؎
    0.47
    Activations Density 0.001%

    No Known Activations