© 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. 32329
    Prev
    Next
    INDEX
    Explanations

    joining words like "us" or "dental"

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

    storage locations

    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
    Ра
    0.58
    Р
    0.56
    Property
    0.55
    РА
    0.54
    R
    0.54
    Raven
    0.54
    ک
    0.52
    О
    0.52
    Ч
    0.51
    רית
    0.50
    POSITIVE LOGITS
     voj
    0.52
     ملے
    0.50
    தலாக
    0.48
     Balliye
    0.47
     renderEncoder
    0.46
     مات
    0.44
     deewana
    0.44
    োত্তর
    0.43
     reiniciar
    0.43
     batal
    0.43
    Activations Density 0.000%

    No Known Activations