© 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. 77633
    Prev
    Next
    INDEX
    Explanations

    understanding actions and relationships

    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
    类型的
    0.49
     radiologists
    0.48
     nesting
    0.46
     প্রজাতির
    0.45
     prothorax
    0.44
     ಎಲ್ಲ
    0.43
    种类
    0.43
    癶
    0.43
    が発生
    0.42
     slouch
    0.42
    POSITIVE LOGITS
    and
    0.71
    r
    0.60
    u
    0.58
    pe
    0.55
    ys
    0.55
    sar
    0.54
    nye
    0.54
    ga
    0.53
    s
    0.53
    पु
    0.52
    Activations Density 0.003%

    No Known Activations