© 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. 8942
    Prev
    Next
    INDEX
    Explanations

    thumbs up or thumb

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

    thumbs up for feedback

    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
    such
    0.62
    a
    0.60
    Σ
    0.56
    lipid
    0.54
    f
    0.54
    spl
    0.52
    Გ
    0.51
    tss
    0.49
    loss
    0.48
    llvm
    0.48
    POSITIVE LOGITS
     thumb
    0.77
     thumbs
    0.68
     Thumb
    0.67
     pouce
    0.61
    ↵
    0.58
     ใช่
    0.54
     يصل
    0.53
     liking
    0.53
    拇
    0.52
    ätzung
    0.51
    Activations Density 0.003%

    No Known Activations