© 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. 11744
    Prev
    Next
    INDEX
    Explanations

    Greeks, Hall, Strawberry

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

    after *

    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
    Notre
    0.29
    emiz
    0.29
    ¾
    0.29
    危険
    0.29
    accueil
    0.28
    ۱
    0.28
    نامه
    0.28
    ‫
    0.28
    safety
    0.27
    素晴らしい
    0.27
    POSITIVE LOGITS
    数据的
    0.36
     second
    0.33
     dacă
    0.33
     divs
    0.33
     headers
    0.33
     FOLLOWING
    0.33
     headerShown
    0.32
     axios
    0.32
     AFTER
    0.32
     THAN
    0.31
    Activations Density 0.001%

    No Known Activations