© 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. 110096
    Prev
    Next
    INDEX
    Explanations

    explaining why

    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
    禣
    0.49
     ответственности
    0.44
     ܘ
    0.43
     ܥ
    0.43
     restante
    0.42
    掣
    0.42
     صرف
    0.41
     दाख
    0.41
    appelijke
    0.41
     України
    0.41
    POSITIVE LOGITS
     blueberry
    0.49
    ;
    0.48
    height
    0.44
    chapter
    0.44
    blueberry
    0.43
    chocolate
    0.42
     paseo
    0.41
     length
    0.41
     bri
    0.41
     eating
    0.41
    Activations Density 0.002%

    No Known Activations