© 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. 70597
    Prev
    Next
    INDEX
    Explanations

    indicate theamount overPenhOverallfeelavidinwisewhich

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

    systems, discussions, and processes

    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
     Kini
    0.57
     Duy
    0.55
     Tas
    0.52
     Kuy
    0.51
     Kus
    0.50
     Graves
    0.49
     肩
    0.49
    o
    0.49
    KEYDOWN
    0.49
     です
    0.48
    POSITIVE LOGITS
     הבי
    0.49
    κής
    0.42
    Deployed
    0.41
    ᾧ
    0.41
    ⴹ
    0.41
    בי
    0.40
    Biography
    0.40
    롬
    0.40
    apai
    0.39
    Биография
    0.39
    Activations Density 0.001%

    No Known Activations