© 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. 161844
    Prev
    Next
    INDEX
    Explanations

    word patterns

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

    expressing emotions or harm

    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
     少し
    0.52
     COLORS
    0.50
    崢
    0.50
     Sadh
    0.49
     Isp
    0.49
     laissent
    0.48
     საშ
    0.48
     странах
    0.47
    礪
    0.47
    だし
    0.46
    POSITIVE LOGITS
    Reactor
    0.46
    Prior
    0.44
    possessed
    0.43
    caused
    0.41
     caused
    0.41
    Proto
    0.41
    Suggestions
    0.41
     aftermath
    0.41
    Responses
    0.41
    Jacques
    0.41
    Activations Density 0.001%

    No Known Activations