© 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. 203682
    Prev
    Next
    INDEX
    Explanations

    sea lion pups, quote, successful, unwanted, flies, treated

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

    comfort suggestions

    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
    喤
    0.48
     Rar
    0.46
    arag
    0.46
     degrades
    0.45
    éclair
    0.44
     റ
    0.44
    芏
    0.44
     socios
    0.44
    rá
    0.43
     fata
    0.43
    POSITIVE LOGITS
     SK
    0.46
    म
    0.45
     Whelan
    0.43
    YES
    0.42
    ma
    0.42
     Jesus
    0.42
    জী
    0.41
    name
    0.41
    లిన
    0.41
    model
    0.41
    Activations Density 0.001%

    No Known Activations