© 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. 131757
    Prev
    Next
    INDEX
    Explanations

    closing angle bracket

    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
    كم
    0.39
    diesel
    0.36
    ეს
    0.36
    ံ
    0.36
    Spray
    0.35
    πος
    0.34
     currentCol
    0.34
    胙
    0.34
    FBSDK
    0.34
     calculus
    0.34
    POSITIVE LOGITS
     Bldg
    0.44
     Building
    0.42
    搂
    0.42
     Scary
    0.41
     scary
    0.38
     acad
    0.37
    Building
    0.37
     ಐ
    0.36
     करू
    0.36
     Presents
    0.36
    Activations Density 0.001%

    No Known Activations