© 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. 163388
    Prev
    Next
    INDEX
    Explanations

    photographs of, arriving at, place in, interface, option to

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

    need, skills, experience, template

    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
    0
    0.57
     मेहनत
    0.46
     vlak
    0.45
    公式
    0.44
     добы
    0.44
     समझा
    0.43
    Rav
    0.43
    {(
    0.43
    совой
    0.43
     Rav
    0.43
    POSITIVE LOGITS
    ivores
    0.49
     reed
    0.43
    ॅमिली
    0.43
    ोरेंट
    0.43
     ಅರ್
    0.42
    ⛄
    0.42
    աս
    0.41
     chicks
    0.41
     Mushrooms
    0.41
     Worcestershire
    0.41
    Activations Density 0.000%

    No Known Activations