© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 168009
    Prev
    Next
    INDEX
    Explanations

    people, actions, and objects

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

    even repeating words

    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
     แถม
    0.52
    ь
    0.50
     pedibus
    0.50
     ยัง
    0.50
     alemão
    0.49
     น่า
    0.48
     همد
    0.48
    🅻
    0.48
    を作成
    0.48
     bientôt
    0.48
    POSITIVE LOGITS
    :}
    0.56
    requested
    0.46
    הר
    0.44
    :]
    0.44
    }
    0.42
    :
    0.42
    ృష్ణ
    0.42
    تف
    0.41
    exhaustive
    0.40
    依据
    0.40
    Activations Density 0.000%

    No Known Activations