© 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. 204350
    Prev
    Next
    INDEX
    Explanations

    new aspect ratio

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

    varying conditions or descriptions

    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
     गेला
    0.48
    чнай
    0.48
    緣
    0.47
    捪
    0.46
    員工
    0.46
    گار
    0.45
    गित
    0.45
     erhältlich
    0.44
    體的
    0.44
    नमस्कार
    0.44
    POSITIVE LOGITS
     variabile
    0.52
     i
    0.52
     सीखना
    0.50
     və
    0.48
     b
    0.47
     h
    0.47
     variable
    0.45
     incrementally
    0.44
     collocation
    0.44
     vary
    0.44
    Activations Density 0.000%

    No Known Activations