© 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. 111372
    Prev
    Next
    INDEX
    Explanations

    breakdown, tokenize

    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
     vzh
    0.46
    替
    0.45
     guinea
    0.45
     ロゴ
    0.45
     第
    0.44
     carav
    0.44
    otonic
    0.42
     observable
    0.41
     однозна
    0.41
    amin
    0.41
    POSITIVE LOGITS
     Lightweight
    0.46
    Not
    0.45
    Blocked
    0.44
    मलव
    0.42
    ইন
    0.42
     Sunlight
    0.41
    <0xE3>
    0.41
     Trained
    0.41
     Blot
    0.41
    Thickness
    0.41
    Activations Density 0.006%

    No Known Activations