© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 70218
    Prev
    Next
    INDEX
    Explanations

    domestic evaluations

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

    indicator of opportunities

    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
    Time
    0.48
    玦
    0.42
    inheritDoc
    0.41
    relativistic
    0.41
    Repr
    0.41
    ﺋ
    0.41
     hurtful
    0.39
    Class
    0.39
     paradoxical
    0.39
    ExprNode
    0.39
    POSITIVE LOGITS
     ৫
    0.57
    ୬
    0.53
     ৪
    0.52
    ៤
    0.50
    ٥
    0.49
    國內
    0.48
     olej
    0.48
     všetky
    0.48
    merksamkeit
    0.47
    响应文件
    0.47
    Activations Density 0.001%

    No Known Activations