© 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. 238660
    Prev
    Next
    INDEX
    Explanations

    punctuation, abbreviations, and some 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
     शोषण
    0.55
    isinde
    0.52
     ப
    0.51
    ที่จะ
    0.51
     যদি
    0.50
     சார்பில்
    0.50
    શું
    0.50
     инфра
    0.50
    фа
    0.49
    ฟ
    0.49
    POSITIVE LOGITS
    祝
    0.42
     hugs
    0.40
     wildflowers
    0.39
    Finn
    0.39
    ridium
    0.38
     melodies
    0.38
    外套
    0.37
    JAM
    0.36
    第二次
    0.36
    愛
    0.36
    Activations Density 0.001%

    No Known Activations