© 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. 6722
    Prev
    Next
    INDEX
    Explanations

    striking simple member onetruly ethnic multi

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

    requiring rollback or requested outside

    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
    Ⲁ
    0.52
    шивания
    0.52
    Ꮵ
    0.49
    Ꮋ
    0.49
    鎳
    0.48
    >]</
    0.47
    IFICATE
    0.47
     রেখেছেন
    0.47
    ༢
    0.47
    Green
    0.46
    POSITIVE LOGITS
     huid
    0.52
    定める
    0.49
     delect
    0.48
     unlock
    0.48
     hiv
    0.47
     nba
    0.46
     iris
    0.46
     juan
    0.45
     angel
    0.45
     append
    0.45
    Activations Density 0.000%

    No Known Activations