© 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. 14889
    Prev
    Next
    INDEX
    Explanations

    erasers

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

    AI learning partner or tutor

    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
    在
    0.64
     in
    0.49
    голо
    0.43
    隆
    0.43
    も
    0.42
    new
    0.41
    小学生
    0.41
    $
    0.41
     new
    0.40
     в
    0.40
    POSITIVE LOGITS
     spender
    0.54
     analisar
    0.52
    Pessoal
    0.52
     analisa
    0.52
     الگ
    0.51
     expliqué
    0.50
     بتایا
    0.47
     affrontare
    0.47
    SPT
    0.47
     analy
    0.47
    Activations Density 0.000%

    No Known Activations