© 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-65K
    7. 51018
    Prev
    Next
    INDEX
    Explanations

    hides or includes

    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_65k_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
    ule
    0.39
    oms
    0.38
    onday
    0.38
    bane
    0.35
    Department
    0.34
    }";
    0.34
    ine
    0.34
    で使用
    0.34
    pit
    0.34
     whence
    0.34
    POSITIVE LOGITS
    zhihu
    0.49
    BASELINE
    0.46
     violent
    0.44
     সাম্প্রদায়িক
    0.44
    鼈
    0.43
     divergence
    0.43
    ▇
    0.43
     reformulation
    0.43
     خی
    0.42
    خیص
    0.42
    Activations Density 0.032%

    No Known Activations