© 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. 77794
    Prev
    Next
    INDEX
    Explanations

    numbers and non-latin characters

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

    charges, justifications, inaccurate, slur

    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
     sinn
    0.43
     routes
    0.42
    ക്കണം
    0.42
    ".[
    0.40
     Able
    0.40
     glows
    0.40
     seas
    0.39
     Kön
    0.39
     hymns
    0.39
     entwickelt
    0.39
    POSITIVE LOGITS
    ０
    0.52
    0
    0.49
     ロ
    0.47
     Президента
    0.47
     ρ
    0.46
    arang
    0.45
    rho
    0.45
     ако
    0.44
    我家
    0.44
    жно
    0.44
    Activations Density 0.000%

    No Known Activations