© 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. 139470
    Prev
    Next
    INDEX
    Explanations

    ran away

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

    a followed by a noun

    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
    FTR
    0.52
    urètre
    0.50
    Overse
    0.49
     Гинд
    0.49
    گم
    0.48
     Halke
    0.47
     ƙ
    0.47
    लिया
    0.46
     Kamane
    0.46
    𝟬
    0.46
    POSITIVE LOGITS
    ave
    0.48
     कोण
    0.44
     flattened
    0.42
    峰
    0.40
    ichtet
    0.40
     কেন্দ্র
    0.40
     plank
    0.40
    কে
    0.39
    ,
    0.39
     developmentally
    0.39
    Activations Density 0.001%

    No Known Activations