© 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. 229177
    Prev
    Next
    INDEX
    Explanations

    most effective

    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
    er
    0.55
    als
    0.48
    erden
    0.46
    ल
    0.46
    ர
    0.45
    प्त
    0.45
     Петер
    0.45
    નિક
    0.44
     Hygiene
    0.44
     hygiene
    0.44
    POSITIVE LOGITS
    ͐
    0.47
    .。
    0.46
    0.46
    。(
    0.45
     同じ
    0.44
    .(
    0.43
     cowl
    0.43
    bn
    0.42
    什麼
    0.42
    ":(
    0.42
    Activations Density 0.001%

    No Known Activations