© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 59462
    Prev
    Next
    INDEX
    Explanations

    legal commentary and analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    reasonable
    0.42
     investig
    0.41
     investigative
    0.41
    (?)
    0.40
    NASA
    0.39
    ஒ
    0.39
    喩
    0.38
    !(
    0.38
    Korea
    0.38
     Investigators
    0.38
    POSITIVE LOGITS
     Lex
    0.54
     Wol
    0.49
     Sweet
    0.46
    wol
    0.44
     commentator
    0.43
     Kluwer
    0.43
     sweet
    0.42
    Wol
    0.41
     Sí
    0.41
     butter
    0.40
    Activations Density 0.001%

    No Known Activations