© 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. 31-GEMMASCOPE-2-RES-262K
    7. 22914
    Prev
    Next
    INDEX
    Explanations

    original biological or client

    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_31_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
     rags
    0.51
     sulfur
    0.51
     whis
    0.49
     clogging
    0.48
     toile
    0.48
     linge
    0.48
     til
    0.48
    ه
    0.47
     calcium
    0.47
     y
    0.46
    POSITIVE LOGITS
    朧
    0.48
    殇
    0.47
    ندر
    0.44
    mapStateToProps
    0.44
    áját
    0.44
     endeavours
    0.44
     currentCol
    0.43
    炖
    0.43
     Betracht
    0.43
    FBSDKSettings
    0.42
    Activations Density 0.000%

    No Known Activations