© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 12556
    Prev
    Next
    INDEX
    Explanations

    testing capabilities

    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
    Collin
    0.43
    Siempre
    0.38
    Gew
    0.37
    ዔ
    0.37
     ощущение
    0.36
    είς
    0.36
    Nub
    0.36
    eric
    0.36
    }):
    0.36
     Nod
    0.36
    POSITIVE LOGITS
     capabilities
    1.33
     abilities
    1.29
     способности
    1.23
     kemampuan
    1.21
     ability
    1.20
    能力
    1.17
     capability
    1.15
    capabilities
    1.09
     क्षमताओं
    1.08
     prowess
    1.07
    Activations Density 0.025%

    No Known Activations