© 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. 21498
    Prev
    Next
    INDEX
    Explanations

    asking questions

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

    Beyond, For, We, So, Artificial

    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
    आइ
    0.45
    щики
    0.40
     filo
    0.39
    <h3>
    0.39
     multil
    0.37
     Layton
    0.36
    INFORM
    0.36
    合う
    0.36
    <h1>
    0.35
    "=>$
    0.35
    POSITIVE LOGITS
    勐
    0.43
    hetics
    0.39
     noted
    0.38
    श्व
    0.38
    cture
    0.38
    不高
    0.38
     इतनी
    0.38
    空氣
    0.38
     प्रकाश
    0.38
     Svet
    0.38
    Activations Density 0.001%

    No Known Activations