© 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. 154184
    Prev
    Next
    INDEX
    Explanations

    multicolanguage words

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

    image alt text or descriptions

    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
    ዝና
    0.50
    leftharpoons
    0.49
    lich
    0.48
    mittel
    0.46
    zás
    0.46
    elés
    0.46
    旣
    0.46
     துவ
    0.45
    zahl
    0.45
    wahl
    0.45
    POSITIVE LOGITS
    ِد
    0.50
     errore
    0.46
     d
    0.46
     quelques
    0.46
     abu
    0.46
    XI
    0.45
     acolo
    0.45
     beberapa
    0.45
     deben
    0.45
     perdita
    0.45
    Activations Density 0.000%

    No Known Activations