© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 187244
    Prev
    Next
    INDEX
    Explanations

    details about links or specific information

    np_acts-logits-general · gemini-2.5-flash-lite

    details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     detailed
    0.61
     dissection
    0.58
     dissect
    0.57
    ↵
    0.55
    }\
    0.54
    !
    0.54
     ].
    0.54
     تجزی
    0.53
     বিশ্লেষণের
    0.52
     Mueller
    0.52
    POSITIVE LOGITS
    म
    0.79
    ام
    0.69
    m
    0.64
    ul
    0.62
    از
    0.59
    ول
    0.58
    其他
    0.56
    뤽
    0.56
    about
    0.55
    OscInitStruct
    0.55
    Activations Density 0.037%

    No Known Activations