© 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. 89115
    Prev
    Next
    INDEX
    Explanations

    notice or, written submissions, ZIP code

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

    Russian adaptations

    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
    ↵
    0.59
    ↵↵
    0.48
     Innov
    0.44
     Interpol
    0.44
     cú
    0.43
     Exploring
    0.43
     exploration
    0.41
     Traffic
    0.41
     Explorer
    0.41
     Moving
    0.40
    POSITIVE LOGITS
    オーナー
    0.56
    Ⅽ
    0.55
     ಅಥವಾ
    0.54
    াসহ
    0.53
    nimi
    0.53
    ዠ
    0.53
     rekomend
    0.53
    𝙲
    0.52
    ⅽ
    0.51
    нное
    0.50
    Activations Density 0.001%

    No Known Activations