© 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. 54914
    Prev
    Next
    INDEX
    Explanations

    h N indices

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

    chemical formulas and notation

    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
     स्थान
    0.47
    ป็น
    0.45
    沦
    0.44
     फिजिक्स
    0.43
    歓
    0.43
     כי
    0.42
     為
    0.42
     เขียน
    0.41
    ถา
    0.41
     कहा
    0.41
    POSITIVE LOGITS
    Default
    0.45
    _{
    0.44
    _
    0.43
    liest
    0.42
     svojih
    0.42
    prev
    0.42
     của
    0.41
    merged
    0.41
    TypeOf
    0.40
    ('_
    0.39
    Activations Density 0.002%

    No Known Activations