© 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. 139289
    Prev
    Next
    INDEX
    Explanations

    character, play, music, stress

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

    specific concepts and instructions

    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
    ↵↵↵↵↵
    0.46
     homogenization
    0.46
    ↵↵↵↵
    0.46
    ↵↵↵↵↵↵↵↵↵↵↵
    0.45
    ↵↵↵
    0.44
    ↵↵↵↵↵↵↵↵↵↵
    0.44
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.42
    you
    0.42
    ↵↵↵↵↵↵↵
    0.41
    魯
    0.41
    POSITIVE LOGITS
    зыка
    0.52
     buzzing
    0.48
     बोलने
    0.48
     grossesse
    0.47
     बिस्तर
    0.47
    allaitement
    0.47
    प्लिक
    0.47
     스트
    0.46
    版权
    0.46
    总理
    0.46
    Activations Density 0.001%

    No Known Activations