© 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. 243171
    Prev
    Next
    INDEX
    Explanations

    regularly, silently, today, critical

    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
    侈
    0.54
    Esse
    0.51
    Mount
    0.49
    ｆ
    0.49
    མ
    0.48
    戲
    0.48
    𝗳
    0.47
    戏
    0.47
    Assassin
    0.47
    А
    0.47
    POSITIVE LOGITS
     condemned
    0.47
     Readers
    0.47
     Yur
    0.47
     condemns
    0.47
     Justices
    0.46
    readers
    0.46
     accorded
    0.46
     Nachdem
    0.46
     Ungarn
    0.45
     Gymn
    0.45
    Activations Density 0.000%

    No Known Activations