© 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. 11193
    Prev
    Next
    INDEX
    Explanations

    academic and descriptive phrasing

    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
     вам
    0.56
     понимают
    0.53
     анали
    0.52
     οπο
    0.52
    踺
    0.52
     има
    0.49
    гах
    0.49
    
    0.49
     описа
    0.49
    }=(-
    0.48
    POSITIVE LOGITS
    1
    0.53
    centered
    0.48
    عمال
    0.47
    ما
    0.47
    packet
    0.47
    ע
    0.46
    married
    0.45
    8
    0.45
     centered
    0.44
    9
    0.44
    Activations Density 0.001%

    No Known Activations