© 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. 204008
    Prev
    Next
    INDEX
    Explanations

    Sink or swim

    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
    во
    0.49
    、
    0.47
    про
    0.46
    Study
    0.45
    Studio
    0.45
    Audio
    0.45
    Pharm
    0.45
    Bl
    0.44
    Media
    0.44
    media
    0.44
    POSITIVE LOGITS
    껀
    0.53
     asfalt
    0.47
     konstruk
    0.45
     Fats
    0.45
     cualquier
    0.44
     स्टेटमेंट
    0.44
     acompan
    0.44
     Kanpur
    0.44
     संतुल
    0.43
     qualquer
    0.43
    Activations Density 0.002%

    No Known Activations