© 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. 121675
    Prev
    Next
    INDEX
    Explanations

    over, not, security, best, sometimes

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

    adhering to guidelines

    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
     ಮಟ್ಟ
    0.58
     individui
    0.55
    ності
    0.53
    ವಿಲ್ಲ
    0.51
     أرض
    0.51
    <unused30>
    0.50
    黴
    0.49
     किरा
    0.48
    𝗵
    0.48
    慓
    0.47
    POSITIVE LOGITS
    opl
    0.48
     hen
    0.48
     megaphone
    0.47
    OR
    0.46
    0
    0.43
    AI
    0.43
    AO
    0.43
    6
    0.43
     he
    0.42
    .*
    0.42
    Activations Density 0.000%

    No Known Activations