© 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. 202180
    Prev
    Next
    INDEX
    Explanations

    long SMA, training data, continued strong

    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
     moderately
    0.41
     concentrate
    0.40
    饪
    0.40
     Kut
    0.38
    ipino
    0.38
    opoulos
    0.38
     hacking
    0.38
    isters
    0.38
     امور
    0.38
    }\|\
    0.37
    POSITIVE LOGITS
    κέ
    0.54
    скім
    0.50
    ５
    0.48
    codewords
    0.47
    ﺘ
    0.46
    レシ
    0.46
    кож
    0.46
    concept
    0.45
     کړ
    0.45
    episode
    0.45
    Activations Density 0.006%

    No Known Activations