© 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. 78330
    Prev
    Next
    INDEX
    Explanations

    ministry foreign China medals

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

    asking permission

    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
    )
    0.47
    ety
    0.43
    转变
    0.42
     n
    0.41
    acter
    0.40
     button
    0.39
     nw
    0.39
     \\
    0.38
    }}
    0.38
    rewrite
    0.38
    POSITIVE LOGITS
     Très
    0.53
    UserProg
    0.52
     thiểu
    0.48
     fêtes
    0.48
    Documentation
    0.48
     ದಾಖ
    0.47
    серва
    0.46
    вере
    0.46
     quarant
    0.46
     InputDecoration
    0.46
    Activations Density 0.001%

    No Known Activations