© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 182051
    Prev
    Next
    INDEX
    Explanations

    volunteers interact

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

    setting up equations or scenarios

    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
    माँ
    0.51
    ’
    0.48
     responsibly
    0.48
     fratern
    0.47
     omitted
    0.46
     সুতরাং
    0.46
     compromise
    0.46
     marketed
    0.46
    ारों
    0.46
     кораб
    0.46
    POSITIVE LOGITS
     fün
    0.44
     கட்டுமான
    0.44
     Tert
    0.43
    лення
    0.42
    喬
    0.42
    這裡是
    0.41
     إلى
    0.40
    不斷
    0.40
    雕
    0.40
    besch
    0.40
    Activations Density 0.001%

    No Known Activations