© 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. 128641
    Prev
    Next
    INDEX
    Explanations

    public garden names

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

    compression, flawed ideas

    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
    मिताभ
    0.46
    ляться
    0.46
     फ़रवरी
    0.46
    ставки
    0.44
     distractions
    0.44
    स्पीड
    0.44
    铤
    0.43
    １
    0.42
    ２
    0.42
    స్త
    0.42
    POSITIVE LOGITS
     giorni
    0.50
    ejb
    0.48
     ある
    0.47
     rifi
    0.47
     मामलों
    0.47
     ده
    0.45
    龐
    0.45
    fashioned
    0.43
    合った
    0.43
     Purse
    0.42
    Activations Density 0.000%

    No Known Activations