© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 71414
    Prev
    Next
    INDEX
    Explanations

    supervision and justice contexts

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

    provides explanation

    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
     écl
    0.54
     éto
    0.45
     frais
    0.45
     c
    0.44
     mellan
    0.44
     deles
    0.44
     convol
    0.43
     belanja
    0.42
     puesta
    0.42
     trova
    0.42
    POSITIVE LOGITS
    Simplified
    0.46
     into
    0.46
    into
    0.44
     ባ
    0.44
    Bootstrap
    0.43
     کی۔
    0.43
     इनटू
    0.42
    Sodium
    0.42
    simplified
    0.41
     Ду
    0.41
    Activations Density 0.001%

    No Known Activations