© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 68730
    Prev
    Next
    INDEX
    Explanations

    legal and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite

    demonstrate, route, categorize, annotate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ข
    0.49
    یو
    0.49
     แค
    0.49
    یا
    0.48
     ఇంకా
    0.46
     แก
    0.46
    ز
    0.45
    <unused2153>
    0.44
     জে
    0.44
     қар
    0.44
    POSITIVE LOGITS
     alleles
    0.55
    માન્ય
    0.48
     meanings
    0.46
    वेदनशील
    0.45
     decisions
    0.42
    धानिक
    0.41
     pravil
    0.41
     populations
    0.40
     probabilities
    0.40
     legumes
    0.40
    Activations Density 0.003%

    No Known Activations