© 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. 70883
    Prev
    Next
    INDEX
    Explanations

    username = variable assignment

    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
     এপ্রিল
    0.52
     ću
    0.46
    쭤
    0.45
     맡
    0.43
     избе
    0.42
    మాట
    0.42
    Quantum
    0.41
    örü
    0.40
    <unused1894>
    0.40
    今日は
    0.40
    POSITIVE LOGITS
     seres
    0.45
    ਾਵ
    0.45
    ෝග
    0.43
     itr
    0.43
     retom
    0.42
     dimes
    0.42
     afsl
    0.41
     traz
    0.41
    ρικ
    0.41
     males
    0.41
    Activations Density 0.007%

    No Known Activations