© 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. 78556
    Prev
    Next
    INDEX
    Explanations

    academic, jargon, formal, money upfront

    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
     countless
    0.55
     and
    0.52
     ataupun
    0.50
    ،
    0.50
     however
    0.50
     và
    0.48
     meticulously
    0.48
    ,
    0.48
     despite
    0.47
     weiterhin
    0.47
    POSITIVE LOGITS
     미리
    0.58
    これから
    0.55
     медицин
    0.53
    अब
    0.49
     ಮುಂದ
    0.49
    镙
    0.49
     гото
    0.49
    妿
    0.49
     necesitan
    0.48
     ఇప్పుడు
    0.48
    Activations Density 0.018%

    No Known Activations