© 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. 8218
    Prev
    Next
    INDEX
    Explanations

    on each

    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
    рів
    0.50
    Faucet
    0.48
    是对
    0.45
     firmly
    0.44
    telek
    0.44
    FundMe
    0.42
     ĝi
    0.42
    畦
    0.42
    כ
    0.41
    કામાં
    0.41
    POSITIVE LOGITS
     प्रकाश
    0.46
     C
    0.44
     Mundo
    0.44
     लाइट्स
    0.43
     new
    0.43
     lights
    0.42
     MMP
    0.42
     Brooks
    0.42
     fre
    0.42
     workforce
    0.41
    Activations Density 0.000%

    No Known Activations