Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 6515
    Prev
    Next
    INDEX
    Explanations

    within input

    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_262k_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
    Predictions
    0.33
    Chúng
    0.33
    ૨
    0.32
    Lorsque
    0.31
    Мы
    0.31
    InterfaceLine
    0.30
    ᅣ
    0.30
    спублі
    0.30
    佲
    0.30
    Polynomial
    0.30
    POSITIVE LOGITS
     but
    0.39
     nhưng
    0.35
     an
    0.34
     pero
    0.33
     لكن
    0.33
     incluso
    0.32
     within
    0.32
     including
    0.32
     controvers
    0.32
     
    0.32
    Activations Density 0.149%

    No Known Activations