© 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. 31123
    Prev
    Next
    INDEX
    Explanations

    finite or discrete concepts

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

    finite or discrete quantities

    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
    frac
    0.47
    two
    0.46
     Sb
    0.45
     Sut
    0.45
    ^{\
    0.44
     Atth
    0.43
    )_{
    0.43
     Ax
    0.42
    hia
    0.42
    祇
    0.42
    POSITIVE LOGITS
     প্রশংস
    0.44
     finite
    0.43
    ัด
    0.43
    चान
    0.41
     kapcsolat
    0.41
    Finite
    0.41
    atkan
    0.40
    ुल्लाह
    0.40
     मारा
    0.40
    ाग्राम
    0.40
    Activations Density 0.002%

    No Known Activations