© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 40296
    Prev
    Next
    INDEX
    Explanations

    .cpp file references

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

    programming code structures

    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
     Jangan
    0.43
     ?
    0.40
     ?,
    0.39
    Jangan
    0.38
    不要
    0.37
    Occ
    0.37
     jangan
    0.37
    Todd
    0.36
     Shad
    0.36
    별
    0.36
    POSITIVE LOGITS
     насыщен
    0.40
    empio
    0.39
     విధంగా
    0.39
    :'],
    0.39
     Schmitz
    0.38
    ஞ
    0.38
     JsonSerializer
    0.38
    彼は
    0.38
     BuzzFeed
    0.37
    ුවන්
    0.37
    Activations Density 0.000%

    No Known Activations