© 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. 14445
    Prev
    Next
    INDEX
    Explanations

    building and design details

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

    listing elements with commas

    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
    ('''
    0.44
    GUAR
    0.43
     위해
    0.43
     quarry
    0.42
     preparado
    0.42
    KSpriteNode
    0.42
     silhouette
    0.42
    ('--
    0.42
    لمانيا
    0.42
     lengthen
    0.42
    POSITIVE LOGITS
     पॉइंट्स
    0.45
    special
    0.45
    橋
    0.44
     লাইন
    0.42
    ător
    0.41
    dır
    0.41
     вокруг
    0.41
    ક્ટ
    0.41
    sampling
    0.41
    vý
    0.41
    Activations Density 0.000%

    No Known Activations