© 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. 124696
    Prev
    Next
    INDEX
    Explanations

    Italian diet, Serb forces

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

    following phrases

    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
    n
    0.51
    eyi
    0.48
    unfinished
    0.46
    of
    0.46
    ln
    0.46
     obtainable
    0.45
     audacious
    0.45
    areth
    0.45
     estuaries
    0.44
    inha
    0.44
    POSITIVE LOGITS
    銃
    0.47
    蠹
    0.47
    Есть
    0.46
    Ва
    0.46
    Время
    0.45
     Sección
    0.45
    Рабо
    0.44
    칩
    0.44
    Дата
    0.44
    Ви
    0.43
    Activations Density 0.001%

    No Known Activations