© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 4851
    Prev
    Next
    INDEX
    Explanations

    default values or behavior

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unterstüt
    0.45
     soutenir
    0.45
    文中
    0.43
    <0x83>
    0.42
    ⬮
    0.42
     představ
    0.41
    WICK
    0.41
    再
    0.41
    Cxx
    0.41
     assertFalse
    0.41
    POSITIVE LOGITS
    ians
    0.45
     сложности
    0.42
     ذاتی
    0.41
    ha
    0.41
     অতীত
    0.41
    нном
    0.41
     ассоциа
    0.41
     handy
    0.41
    em
    0.40
    ina
    0.40
    Activations Density 0.023%

    No Known Activations