© 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. 37943
    Prev
    Next
    INDEX
    Explanations

    to hear them

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

    white stripe and chocolate

    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
     i
    0.69
     {
    0.48
     kT
    0.48
     kullan
    0.48
     $
    0.48
    1
    0.48
     —,
    0.47
     !
    0.47
     ili
    0.47
     recursive
    0.46
    POSITIVE LOGITS
    CellStyle
    0.52
    lação
    0.50
    itent
    0.48
    ょう
    0.48
    මාණය
    0.48
    仴
    0.47
    бри
    0.47
    ље
    0.46
    煊
    0.46
    डाउन
    0.46
    Activations Density 0.000%

    No Known Activations