© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 131601
    Prev
    Next
    INDEX
    Explanations

    UI elements and "attention"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    clas
    0.39
    谤
    0.39
    उस
    0.37
    labelled
    0.37
     Commandant
    0.37
    ૃ
    0.37
    lette
    0.36
    璟
    0.36
    omis
    0.36
    lbrace
    0.36
    POSITIVE LOGITS
     grid
    0.42
    ണ്ഡി
    0.41
     residing
    0.37
     jì
    0.37
     reside
    0.36
     overestimate
    0.36
     responding
    0.36
     racing
    0.35
     crank
    0.35
    보험
    0.35
    Activations Density 0.001%

    No Known Activations