© 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-65K
    7. 52837
    Prev
    Next
    INDEX
    Explanations

    equipment, resources, fitness

    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_65k_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
    tral
    0.42
     Redeem
    0.40
    啜
    0.39
    рта
    0.39
    莼
    0.38
     MacDonald
    0.38
    సా
    0.38
    ण्यास
    0.37
     pictorial
    0.37
     وحدة
    0.37
    POSITIVE LOGITS
    indent
    0.45
    霏
    0.45
    accum
    0.44
     inherits
    0.43
    focus
    0.42
     inherit
    0.41
    LaTeX
    0.40
    ="",
    0.40
    ="")
    0.40
     grafting
    0.39
    Activations Density 0.007%

    No Known Activations