© 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. 218868
    Prev
    Next
    INDEX
    Explanations

    stellar mass and human resources

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

    avoid splitting 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
    c
    0.59
    n
    0.57
    h
    0.53
    b
    0.53
    t
    0.52
    done
    0.49
    笑
    0.49
    k
    0.48
    g
    0.48
     rubbed
    0.47
    POSITIVE LOGITS
     ខ
    0.45
    冠軍
    0.45
     livre
    0.45
     planas
    0.45
     نرخ
    0.44
     ضلع
    0.44
     ALPINE
    0.44
     kapital
    0.43
     кей
    0.42
     lutte
    0.42
    Activations Density 0.001%

    No Known Activations