© 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. 190562
    Prev
    Next
    INDEX
    Explanations

    advice and actions

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

    frequently implicated but they

    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
    veratrol
    0.49
     kuş
    0.46
     positively
    0.45
     halftone
    0.45
    썰
    0.45
     tük
    0.44
     kés
    0.43
     万元
    0.43
    ärk
    0.43
     输出
    0.42
    POSITIVE LOGITS
    রামর্শ
    0.48
    T
    0.47
    Villa
    0.47
     oversized
    0.46
    ನಿಯ
    0.44
     অনেকে
    0.43
     বাইরের
    0.43
    我的
    0.42
     বিদ্রোহীদের
    0.42
    リーダー
    0.42
    Activations Density 0.000%

    No Known Activations