© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 223422
    Prev
    Next
    INDEX
    Explanations

    mentions of usernames and support

    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
    स्थ
    0.37
    staticfiles
    0.37
    located
    0.37
    ...............
    0.36
    ................
    0.35
    ^{\
    0.35
    하거나
    0.35
    obacteria
    0.34
    determine
    0.34
    sensitive
    0.34
    POSITIVE LOGITS
     Haha
    0.63
     yeah
    0.59
     hahaha
    0.57
     yep
    0.56
    ⁩
    0.56
     ถ้า
    0.56
     hmm
    0.55
     спасибо
    0.54
     如果
    0.54
     yes
    0.54
    Activations Density 0.001%

    No Known Activations