© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 9205
    Prev
    Next
    INDEX
    Explanations

    variables and formulas

    np_acts-logits-general · gemini-2.5-flash-lite

    mathematical formulas and operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    职务
    0.55
     публі
    0.55
    赈
    0.55
    众人
    0.54
    狨
    0.54
    acariy
    0.53
    戏剧
    0.53
    鹜
    0.53
    Downtown
    0.52
    俭
    0.52
    POSITIVE LOGITS
    sqrt
    0.68
     coefficients
    0.64
     C
    0.63
     sqrt
    0.63
     distance
    0.62
     coefficient
    0.62
     P
    0.61
     c
    0.59
     constants
    0.59
     T
    0.58
    Activations Density 0.023%

    No Known Activations