© 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. 110323
    Prev
    Next
    INDEX
    Explanations

    asking questions

    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
     Innovation
    0.42
    THER
    0.41
    電力
    0.39
     ዓይ
    0.39
    ','%
    0.39
     remainder
    0.39
    រយៈពេល
    0.39
    ardin
    0.38
    zaXRvcn
    0.38
    ಜಿ
    0.37
    POSITIVE LOGITS
    판
    0.52
    ņu
    0.49
    라
    0.47
    cru
    0.45
     been
    0.44
     !!!!
    0.44
     otra
    0.44
     hospitalization
    0.43
    ੁੰ
    0.43
     falou
    0.43
    Activations Density 0.001%

    No Known Activations