© 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. 9684
    Prev
    Next
    INDEX
    Explanations

    straight, cozy, small, favorably

    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
     તથા
    0.35
     ಹಾಗೂ
    0.32
     সম্বন্ধে
    0.31
     egli
    0.30
    こうした
    0.30
    --
    0.30
     sämt
    0.30
     riguardo
    0.29
    Might
    0.29
     regard
    0.29
    POSITIVE LOGITS
     ​​
    0.62
     XNUMX
    0.55
     ​​​​
    0.47
    NUMX
    0.46
     ፣
    0.36
     .:
    0.35
     carefree
    0.35
     Undoubtedly
    0.34
     disappears
    0.34
     FullHD
    0.34
    Activations Density 0.015%

    No Known Activations