© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 37739
    Prev
    Next
    INDEX
    Explanations

    describing outcomes and capabilities

    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
     décadas
    0.56
     scorso
    0.56
    意志
    0.51
    чис
    0.51
    爿
    0.49
    ιο
    0.48
     signalé
    0.48
    decade
    0.48
    вні
    0.47
    ู
    0.47
    POSITIVE LOGITS
     מש
    0.52
    </h1>
    0.49
    </h3>
    0.49
    </th>
    0.48
     लेबल
    0.46
     desorption
    0.44
    </h4>
    0.44
     التع
    0.44
     অধ্যয়ন
    0.44
     מ
    0.44
    Activations Density 0.001%

    No Known Activations