© 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. 7451
    Prev
    Next
    INDEX
    Explanations

    equations and calculations

    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
     invari
    0.45
    羋
    0.44
    ྵ
    0.44
    韜
    0.43
    beding
    0.42
     განს
    0.42
    ksz
    0.42
    ﹕
    0.41
     leptonic
    0.41
     داستان
    0.41
    POSITIVE LOGITS
    ↵
    0.37
     Breakdown
    0.36
    0.36
     Modelo
    0.35
     него
    0.35
     Week
    0.35
     School
    0.34
     Charts
    0.34
     Airplane
    0.34
     Year
    0.34
    Activations Density 0.006%

    No Known Activations