© 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. 157828
    Prev
    Next
    INDEX
    Explanations

    July 13, interested in

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

    situation, "question", "Lua"

    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
     live
    0.45
    SAS
    0.43
     that
    0.43
     digit
    0.42
     certa
    0.42
     a
    0.42
     fertil
    0.42
    പ്പെടുന്ന
    0.42
     sediments
    0.41
    capability
    0.41
    POSITIVE LOGITS
     éxitos
    0.47
    வித்து
    0.47
     violación
    0.46
    ллі
    0.44
    íí
    0.44
     Buchstaben
    0.44
    ног
    0.43
    란드
    0.43
    滥
    0.43
    收款
    0.43
    Activations Density 0.000%

    No Known Activations