© 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. 247749
    Prev
    Next
    INDEX
    Explanations

    ten minutes, attic door

    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
    睡眠
    0.45
    Ნ
    0.45
    𝜁
    0.44
    预测
    0.44
    什么时候
    0.43
    Ⲛ
    0.43
    挚
    0.43
    ንስ
    0.43
    hnt
    0.43
    pinch
    0.43
    POSITIVE LOGITS
     bru
    0.50
     בן
    0.45
     coats
    0.45
     boas
    0.44
     woods
    0.43
     fort
    0.42
     publié
    0.42
     allem
    0.42
     subsidiaries
    0.42
     chartered
    0.41
    Activations Density 0.000%

    No Known Activations