© 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. 97759
    Prev
    Next
    INDEX
    Explanations

    less than, likely to, verify your

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

    middle eastern, adults, troubleshooting, active, shingles, complex, parallel, detection

    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
    tuples
    0.47
     ຊ
    0.44
     бол
    0.43
     допомогти
    0.43
    쁠
    0.43
     евре
    0.43
    Caching
    0.42
    Visiting
    0.42
    ⛷
    0.42
    🎿
    0.42
    POSITIVE LOGITS
     jinak
    0.49
     paraly
    0.49
     nya
    0.47
     brahman
    0.47
     Fakult
    0.47
     Fuk
    0.47
     núcleos
    0.47
     Fakultas
    0.46
     materi
    0.46
     nowe
    0.46
    Activations Density 0.000%

    No Known Activations