© 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. 31-GEMMASCOPE-2-RES-262K
    7. 202237
    Prev
    Next
    INDEX
    Explanations

    friction, mucus, particles, water

    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
    षु
    0.46
    ≤</
    0.44
     sacr
    0.44
    animity
    0.43
     Âu
    0.42
     nécessité
    0.42
    لد
    0.42
     සැල
    0.42
     rédu
    0.42
    사이
    0.42
    POSITIVE LOGITS
    \
    0.44
    program
    0.43
     αυτά
    0.41
    id
    0.41
    interval
    0.40
    unan
    0.40
    \'
    0.40
    framework
    0.39
    end
    0.39
    êm
    0.39
    Activations Density 0.001%

    No Known Activations