© 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. 148817
    Prev
    Next
    INDEX
    Explanations

    completion and celebration

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

    greetings and introductions

    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
    Not in Any Lists

    No Comments

    Negative Logits
     а
    0.47
     ним
    0.45
    ам
    0.45
    度
    0.44
    灿
    0.44
    сова
    0.44
     dint
    0.43
     disbelief
    0.43
    úsc
    0.43
     Рим
    0.43
    POSITIVE LOGITS
     mohou
    0.48
     działa
    0.47
     pourraient
    0.45
    ēja
    0.45
     pohy
    0.44
    รุ่น
    0.43
     bringt
    0.43
     চৌ
    0.42
    ✂
    0.42
    nection
    0.42
    Activations Density 0.000%

    No Known Activations