© 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. 15347
    Prev
    Next
    INDEX
    Explanations

    comprehensive but

    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
    arser
    0.40
    שית
    0.38
    Reduction
    0.35
    🥜
    0.34
    emics
    0.33
    amenti
    0.33
     συμ
    0.33
    <{
    0.32
    atthakath
    0.32
    au
    0.32
    POSITIVE LOGITS
     but
    2.06
     nhưng
    1.89
    但不
    1.85
     mutta
    1.78
    แต่
    1.76
     ngunit
    1.72
     pero
    1.68
     ولكن
    1.66
     אך
    1.65
    but
    1.63
    Activations Density 0.254%

    No Known Activations