© 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. 21183
    Prev
    Next
    INDEX
    Explanations

    node followed by punctuation

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

    LZW encoding and compression

    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
    uição
    0.45
     u
    0.43
     held
    0.41
     Kont
    0.41
    а
    0.41
    鋆
    0.40
    atively
    0.40
    п
    0.40
     h
    0.39
    uação
    0.39
    POSITIVE LOGITS
     انر
    0.50
     yù
    0.48
    schedule
    0.48
     پہا
    0.48
     تمہیں
    0.47
     سلاټ
    0.47
    jg
    0.47
     목록
    0.46
     companionship
    0.46
    ೂ
    0.45
    Activations Density 0.000%

    No Known Activations