© 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. 148556
    Prev
    Next
    INDEX
    Explanations

    multilingual and technical terms

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

    code structures, punctuation, and specific words

    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
     downsizing
    0.52
    เพิ่ม
    0.46
     pak
    0.45
     pakk
    0.45
    แผน
    0.45
    Pak
    0.43
    軫
    0.43
    Tech
    0.42
    Ook
    0.42
     teor
    0.42
    POSITIVE LOGITS
     때문에
    0.59
     병
    0.54
     Boulder
    0.52
     Университе
    0.52
     ImageView
    0.50
     Quỳnh
    0.50
    ształ
    0.49
    isEmpty
    0.49
     သင်
    0.48
     आहेत
    0.47
    Activations Density 0.000%

    No Known Activations