© 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. 24012
    Prev
    Next
    INDEX
    Explanations

    math concepts and values

    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
     Agree
    0.44
     Directly
    0.41
    仡
    0.40
     كت
    0.38
     Duplicate
    0.38
    ypeł
    0.38
    可能會
    0.36
     شيء
    0.36
     způsob
    0.36
    だけで
    0.36
    POSITIVE LOGITS
    overview
    0.43
    linear
    0.42
     linear
    0.42
     abstraction
    0.41
     sportswear
    0.41
    ultural
    0.40
     studs
    0.40
    概
    0.40
    Articles
    0.39
     metabolism
    0.39
    Activations Density 0.000%

    No Known Activations