© 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. 135408
    Prev
    Next
    INDEX
    Explanations

    possessive and common connective words

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

    fluid flow and obstacles

    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
    執行
    0.49
    家伙
    0.48
    してた
    0.46
    짰
    0.46
    ੦
    0.46
    確實
    0.45
    كُمْ
    0.43
    詞
    0.43
    ଐ
    0.43
    जिये
    0.42
    POSITIVE LOGITS
    Br
    0.50
    Eight
    0.48
    De
    0.48
    Rolling
    0.47
    Running
    0.46
     इनकम
    0.46
    TimeStamp
    0.46
    TypeValue
    0.45
     uniques
    0.45
     Villan
    0.44
    Activations Density 0.000%

    No Known Activations