© 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-262K
    7. 125423
    Prev
    Next
    INDEX
    Explanations

    harming others or discussing slavery

    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
    a
    0.51
    题材
    0.47
    する方法
    0.46
     Ballon
    0.45
    辦法
    0.42
     Metaverse
    0.42
     Fires
    0.42
     setCount
    0.42
    昻
    0.41
    port
    0.39
    POSITIVE LOGITS
    czę
    0.45
     hade
    0.45
    XH
    0.45
    LED
    0.44
    flav
    0.44
    แสง
    0.43
     frå
    0.43
     kep
    0.43
     něm
    0.43
     purchases
    0.42
    Activations Density 0.002%

    No Known Activations