© 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. 35914
    Prev
    Next
    INDEX
    Explanations

    state changes

    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
    낄
    0.39
    助
    0.38
    েজ
    0.38
    érios
    0.37
    dot
    0.37
     doivent
    0.36
    вига
    0.36
     répart
    0.36
    龇
    0.36
    őd
    0.36
    POSITIVE LOGITS
     turn
    0.73
    Turn
    0.71
    turn
    0.69
     turnaround
    0.68
     Turn
    0.66
     TURN
    0.64
     turnover
    0.59
    turned
    0.58
    转
    0.58
    TURN
    0.57
    Activations Density 0.000%

    No Known Activations