© 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. 7936
    Prev
    Next
    INDEX
    Explanations

    general materials and structures

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

    controlling print end parameter

    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
     अद्भ
    0.45
    w
    0.43
    𝔼
    0.41
     trivially
    0.41
     swapped
    0.41
    ích
    0.41
    g
    0.40
    k
    0.40
     रोमा
    0.40
    ải
    0.39
    POSITIVE LOGITS
     solar
    0.46
    Solar
    0.45
     uniquement
    0.43
     Solar
    0.42
     viktigt
    0.41
     meille
    0.41
    িকে
    0.41
     ನಾವು
    0.41
     townhouse
    0.41
    เสมอ
    0.40
    Activations Density 0.000%

    No Known Activations