© 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. 32193
    Prev
    Next
    INDEX
    Explanations

    html markup and code examples

    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
     Gym
    0.46
     Paradox
    0.42
     CSS
    0.41
     Mystery
    0.40
     "<
    0.40
     BlogPost
    0.39
     Anchor
    0.38
     Criteria
    0.37
     ♪
    0.37
    pleri
    0.37
    POSITIVE LOGITS
     obscene
    0.45
    takePhotoButton
    0.44
    Curso
    0.40
    ㇁
    0.40
    trimethyl
    0.40
    ulence
    0.39
     articulate
    0.39
    appearance
    0.39
    ได
    0.39
    http
    0.38
    Activations Density 0.000%

    No Known Activations