© 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. 16036
    Prev
    Next
    INDEX
    Explanations

    . and Site

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

    code snippets

    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
    Pda
    0.38
    Bechyné
    0.38
    SendData
    0.38
    渠
    0.36
     উদ্ভিদ
    0.36
    ॉप
    0.36
    続ける
    0.35
    ᚄ
    0.35
    strument
    0.34
    PDA
    0.34
    POSITIVE LOGITS
     c
    0.38
     ج
    0.36
     মাতৃ
    0.36
     Sehr
    0.35
     j
    0.34
     Rid
    0.34
     Si
    0.34
     megy
    0.34
     Mi
    0.33
     Rup
    0.33
    Activations Density 0.028%

    No Known Activations