© 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. 70609
    Prev
    Next
    INDEX
    Explanations

    online security threats

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

    generalizations and narratives

    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
    3
    0.56
    8
    0.53
    ۹
    0.50
    classified
    0.48
    4
    0.47
     revel
    0.47
    caliber
    0.47
    9
    0.47
    hopping
    0.45
    party
    0.44
    POSITIVE LOGITS
    膯
    0.50
    釟
    0.49
    瓈
    0.49
    Extern
    0.48
    Các
    0.47
    Ἠ
    0.47
    欧
    0.47
    Gün
    0.46
    虽
    0.46
    烜
    0.46
    Activations Density 0.001%

    No Known Activations