© 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. 18312
    Prev
    Next
    INDEX
    Explanations

    variations of others

    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
    the
    0.57
    ها
    0.55
    .
    0.55
    ті
    0.53
    age
    0.52
    source
    0.52
    на
    0.52
    اا
    0.51
    y
    0.51
    ou
    0.49
    POSITIVE LOGITS
     others
    0.61
     bicovariant
    0.52
     інших
    0.51
     altri
    0.50
     otras
    0.50
     eius
    0.49
     otros
    0.48
     altres
    0.47
     drugih
    0.47
     anderes
    0.47
    Activations Density 0.032%

    No Known Activations