© 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. 51798
    Prev
    Next
    INDEX
    Explanations

    These two

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

    related to concepts

    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
     sebi
    0.54
    stev
    0.46
     ನೋಡ
    0.46
     وول
    0.45
    бро
    0.45
     misplaced
    0.45
    ことも
    0.43
    ﺗ
    0.43
    ジット
    0.43
    譚
    0.43
    POSITIVE LOGITS
    otions
    0.55
    ὃ
    0.48
    ὧ
    0.46
    oción
    0.45
    odoro
    0.44
     Theology
    0.44
    ournal
    0.42
     Todos
    0.42
     várias
    0.42
    hesu
    0.42
    Activations Density 0.000%

    No Known Activations