© 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. 204036
    Prev
    Next
    INDEX
    Explanations

    vision, sound, and touch

    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
    flows
    0.50
    f
    0.50
     k
    0.47
    al
    0.46
    },\
    0.46
     K
    0.45
     \
    0.45
     R
    0.44
    flo
    0.44
    }\
    0.44
    POSITIVE LOGITS
    飒
    0.52
     ঠান্ডা
    0.45
    তখন
    0.45
     areal
    0.44
    糈
    0.44
     diferença
    0.42
     unterscheiden
    0.42
    따
    0.42
    蘅
    0.42
    কেশন
    0.42
    Activations Density 0.004%

    No Known Activations