© 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. 218949
    Prev
    Next
    INDEX
    Explanations

    financial revenues and budgets

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

    operations and accounts

    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
    舉
    0.46
    blah
    0.46
    ämä
    0.44
    orton
    0.44
    0.43
    levi
    0.42
    zł
    0.42
    )))
    0.41
    发
    0.41
    this
    0.41
    POSITIVE LOGITS
    седнев
    0.57
     LDGs
    0.54
    ленных
    0.52
     всех
    0.50
    لڈ
    0.50
     ciudades
    0.50
     convexes
    0.50
     станов
    0.50
     الاكس
    0.49
    жены
    0.49
    Activations Density 0.000%

    No Known Activations