© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 77817
    Prev
    Next
    INDEX
    Explanations

    measurement, air, strings, securities, calculating parity, rice

    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
     später
    0.50
    </h3>
    0.45
     är
    0.45
     വിൽപ്പന
    0.44
     далее
    0.43
     ohne
    0.41
     bü
    0.41
     Zoll
    0.41
     later
    0.40
     është
    0.40
    POSITIVE LOGITS
    사의
    0.43
    ფორ
    0.42
    사가
    0.42
    빻
    0.42
    oug
    0.41
    زن
    0.41
     constancy
    0.41
    produced
    0.41
     introductory
    0.40
     ভাত
    0.40
    Activations Density 0.002%

    No Known Activations