© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 3850
    Prev
    Next
    INDEX
    Explanations

    overly + adjective

    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/layer_31_width_262k_l0_medium
    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
     mates
    0.48
    ா
    0.47
     funders
    0.47
     THINGS
    0.47
    ccione
    0.47
     propiedad
    0.46
    ে
    0.46
    平安
    0.46
     tenido
    0.45
     communities
    0.45
    POSITIVE LOGITS
     психо
    0.47
    psych
    0.47
     البريط
    0.47
    processor
    0.46
     steril
    0.44
     ឬ
    0.44
    ToSort
    0.43
     లా
    0.43
    lau
    0.42
    or
    0.42
    Activations Density 0.001%

    No Known Activations