© 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. 211342
    Prev
    Next
    INDEX
    Explanations

    person tutor

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

    HTML structure tags

    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
     raat
    0.57
     strategia
    0.51
    m
    0.51
    vi
    0.50
     struktur
    0.49
    il
    0.49
    jons
    0.47
    l
    0.46
    mila
    0.45
     strategie
    0.45
    POSITIVE LOGITS
     цього
    0.50
     этого
    0.41
    скім
    0.41
     आयुक्त
    0.39
    ordered
    0.39
     છે
    0.39
     ۱۰
    0.38
     सज्
    0.38
    りたい
    0.38
     This
    0.38
    Activations Density 0.000%

    No Known Activations