© 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. 7338
    Prev
    Next
    INDEX
    Explanations

    end punctuation

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

    actions and states

    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
     ataupun
    0.41
     veya
    0.38
     किंवा
    0.38
    하거나
    0.36
    或
    0.35
     หรือ
    0.35
     vagy
    0.34
     või
    0.34
     或
    0.34
     atau
    0.33
    POSITIVE LOGITS
    。
    0.43
    。「
    0.35
    。『
    0.33
    .
    0.33
    ។
    0.33
     whereupon
    0.32
    ．
    0.32
    ։
    0.31
    ৷
    0.29
    แล้ว
    0.28
    Activations Density 0.261%

    No Known Activations