© 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. 12801
    Prev
    Next
    INDEX
    Explanations

    digital logic representation

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

    AI writing and content generation

    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
     permit
    0.48
     Anschließend
    0.47
     Permit
    0.47
     Toxicol
    0.47
     Mull
    0.44
    s
    0.43
     Perm
    0.43
    Ϭ
    0.43
     Saves
    0.42
    r
    0.42
    POSITIVE LOGITS
     analyzing
    0.52
     maintenir
    0.48
    UDE
    0.47
     analysing
    0.46
    ಕೋ
    0.46
     realizzare
    0.46
    Merci
    0.45
     analizar
    0.44
    alternate
    0.44
    兢
    0.44
    Activations Density 0.000%

    No Known Activations