© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 6733
    Prev
    Next
    INDEX
    Explanations

    configuration options

    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
     함
    0.29
     revela
    0.27
     História
    0.27
     lucu
    0.26
     विद्यार्थी
    0.26
     Elektrokhimiya
    0.26
     emotionally
    0.26
     Gertrude
    0.26
     Handlung
    0.26
     ا
    0.26
    POSITIVE LOGITS
    Enable
    0.37
    enable
    0.34
    max
    0.34
     enabled
    0.31
    enabled
    0.31
    设置
    0.31
    opaque
    0.31
    protect
    0.30
    force
    0.30
    bypass
    0.30
    Activations Density 0.330%

    No Known Activations