© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 217299
    Prev
    Next
    INDEX
    Explanations

    various conditions

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

    prohibits punishing others

    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
     сообщили
    0.57
     Điện
    0.52
     ඇ
    0.51
     விற்ப
    0.49
     ລ
    0.48
     điện
    0.47
     berichten
    0.46
     электри
    0.46
     전기
    0.46
    ıları
    0.46
    POSITIVE LOGITS
     blindness
    0.45
     pobre
    0.44
     malades
    0.43
    prueba
    0.43
     sufferers
    0.43
    當時
    0.42
     poor
    0.42
    日々
    0.42
     maj
    0.42
    炲
    0.42
    Activations Density 0.001%

    No Known Activations