© 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. 154319
    Prev
    Next
    INDEX
    Explanations

    justaindustrialfecesmealfrosting

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

    Regulation, sense, girls, easily, often, generally

    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
     makeSound
    0.43
    colors
    0.43
     Lembrando
    0.43
     가수
    0.42
    Iterator
    0.42
    ını
    0.41
    ٹ
    0.41
    흐
    0.41
     Iterator
    0.41
    ב
    0.41
    POSITIVE LOGITS
    ба
    0.52
    ద్దా
    0.49
    рма
    0.48
     pouvait
    0.48
     barred
    0.46
     nationalist
    0.45
    方針
    0.45
    пта
    0.45
    で開催
    0.44
     separatist
    0.44
    Activations Density 0.001%

    No Known Activations