© 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. 200010
    Prev
    Next
    INDEX
    Explanations

    authorization, preauthorization, card, surge

    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
    䡒
    0.53
    劷
    0.48
    圻
    0.47
    व्य
    0.47
    )=(\
    0.46
    우스
    0.45
    嚩
    0.45
    setFooter
    0.44
    𝐰
    0.44
     червня
    0.44
    POSITIVE LOGITS
     manuals
    0.62
     authorization
    0.60
     be
    0.57
     watches
    0.57
     composite
    0.55
     forces
    0.55
     magnes
    0.54
     integral
    0.53
     planets
    0.53
     backlash
    0.53
    Activations Density 0.000%

    No Known Activations