© 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. 4770
    Prev
    Next
    INDEX
    Explanations

    neuro and psycho terms

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

    neuro, electro, hydro, geo prefixes

    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
    绛
    0.43
     Hochzeit
    0.40
    禳
    0.40
     минус
    0.38
     Tử
    0.38
     Türkei
    0.38
    拶
    0.37
     Newspapers
    0.37
     exceptionnelle
    0.37
     মুক্তিফৌজ
    0.37
    POSITIVE LOGITS
    -
    0.46
    TO
    0.44
    \
    0.42
    RI
    0.41
    ological
    0.41
    MO
    0.40
    }
    0.40
    LI
    0.40
    CO
    0.39
    end
    0.39
    Activations Density 0.049%

    No Known Activations