© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 7172
    Prev
    Next
    INDEX
    Explanations

    block of code

    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_all/layer_41_width_262k_l0_big
    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
    ≌
    0.37
     maxWidth
    0.31
    వలం
    0.31
    嬲
    0.30
     raya
    0.30
    
    0.30
    嬙
    0.30
    ◁
    0.30
    ^_^
    0.29
    廛
    0.29
    POSITIVE LOGITS
     block
    0.53
    block
    0.51
    Block
    0.48
     blocks
    0.44
     Block
    0.43
     Why
    0.42
    blocks
    0.41
     What
    0.41
     How
    0.40
     functions
    0.39
    Activations Density 0.001%

    No Known Activations