© 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. 14876
    Prev
    Next
    INDEX
    Explanations

    states, requirements, or consequences

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

    creating visually informative graphics

    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
     همکاری
    0.46
     डिवा
    0.43
    ingles
    0.42
     ブリ
    0.42
    numer
    0.42
    asile
    0.41
     Choud
    0.41
    㞖
    0.40
    <unused207>
    0.40
     digitalization
    0.39
    POSITIVE LOGITS
     kü
    0.42
     TypeError
    0.42
     +"
    0.40
    EXCEPTION
    0.38
     nhắn
    0.38
    嘟
    0.38
    TYPE
    0.37
    (*)
    0.37
     Loài
    0.37
     način
    0.37
    Activations Density 0.000%

    No Known Activations