© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 56643
    Prev
    Next
    INDEX
    Explanations

    tqdm and code progress

    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
    Primary
    0.45
    ามารถ
    0.44
    دم
    0.43
    rmsg
    0.43
    тол
    0.43
    glyphicon
    0.42
    么
    0.42
    getName
    0.42
    مس
    0.42
     Primary
    0.41
    POSITIVE LOGITS
     &\
    0.45
    कुछ
    0.45
    ‣
    0.42
    ➛
    0.41
     punctu
    0.41
     attain
    0.40
     деше
    0.40
     जवळ
    0.40
     ונ
    0.39
     puntual
    0.39
    Activations Density 0.001%

    No Known Activations