© 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. 221455
    Prev
    Next
    INDEX
    Explanations

    percentages and numeric distributions

    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
    ⊠
    0.42
     Boltzmann
    0.41
     사회
    0.41
     ಮೂಲ
    0.38
     मुस्लिम
    0.38
    公务
    0.38
     అధికార
    0.36
    痪
    0.36
    PROTON
    0.36
     allgemeinen
    0.36
    POSITIVE LOGITS
    ero
    0.39
    roč
    0.39
     Micro
    0.38
    micro
    0.37
    twenty
    0.37
    crow
    0.36
    habitude
    0.36
    Micro
    0.36
    ્રો
    0.35
    вающей
    0.35
    Activations Density 0.014%

    No Known Activations