© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 58300
    Prev
    Next
    INDEX
    Explanations

    foreign languages and some English

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

    response starting with okay

    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
     tanda
    0.51
     soot
    0.51
    ँकि
    0.48
    .$\
    0.47
     gelin
    0.46
     nephews
    0.44
     juta
    0.43
     pung
    0.43
     thermos
    0.43
     selanjutnya
    0.42
    POSITIVE LOGITS
     ويل
    0.48
    𝐢
    0.48
    ка
    0.46
    𝐚
    0.46
     crafting
    0.45
     váš
    0.45
    Trac
    0.45
    lement
    0.45
    Carl
    0.45
     evolucion
    0.44
    Activations Density 0.000%

    No Known Activations