© 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. 16296
    Prev
    Next
    INDEX
    Explanations

    ironically, notably, ideally, generally

    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
     Kd
    0.38
     EYE
    0.37
     sensibilities
    0.36
     FLOR
    0.36
     Renn
    0.36
     P
    0.35
    вот
    0.35
    ിക്കുകയും
    0.34
     quarters
    0.33
    သို့
    0.33
    POSITIVE LOGITS
     falando
    0.79
     hablando
    0.61
    ၊
    0.58
     speaking
    0.55
    ،
    0.55
     önemlidir
    0.54
     houve
    0.53
    情况下
    0.52
    weds
    0.52
    ,
    0.52
    Activations Density 0.014%

    No Known Activations