© 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. 40-GEMMASCOPE-2-RES-262K
    7. 195693
    Prev
    Next
    INDEX
    Explanations

    infinitely many

    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_40_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
     >
    0.48
    >
    0.43
    />
    0.42
    狂
    0.40
    ()>
    0.38
     />
    0.38
    Ind
    0.37
    很久
    0.36
    $>
    0.36
     সপ্তাহ
    0.36
    POSITIVE LOGITS
     infinitely
    0.62
     infinite
    0.55
    infinite
    0.50
    无数
    0.49
     plethora
    0.48
     많
    0.48
     অসংখ্য
    0.46
     multitude
    0.45
     countless
    0.44
     plentiful
    0.44
    Activations Density 0.015%

    No Known Activations