© 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. 31-GEMMASCOPE-2-RES-262K
    7. 10927
    Prev
    Next
    INDEX
    Explanations

    code structure labels

    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_31_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
    废
    0.41
     रेट
    0.39
    果
    0.38
     解析
    0.38
    Otros
    0.38
    För
    0.37
    டித்து
    0.37
    OSH
    0.37
    ärte
    0.37
     Stabilization
    0.37
    POSITIVE LOGITS
    :
    0.44
    '
    0.42
     and
    0.41
    tains
    0.39
    ):
    0.39
     inmobili
    0.38
     financ
    0.37
     bahwa
    0.37
    ورو
    0.37
     holde
    0.37
    Activations Density 0.029%

    No Known Activations