© 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. 143219
    Prev
    Next
    INDEX
    Explanations

    bulk bags

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

    inverse Fourier transform

    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
    ע
    0.52
    ان
    0.51
    ار
    0.49
    ع
    0.46
    قدر
    0.45
    位
    0.44
    ар
    0.43
    1
    0.42
    уд
    0.42
    不良
    0.41
    POSITIVE LOGITS
     ਸਾ
    0.54
     cadast
    0.53
     mathematical
    0.51
     Aeron
    0.51
     Mathematical
    0.50
    designated
    0.50
     Conceptual
    0.50
     standardization
    0.49
     thursday
    0.49
     guaranteeing
    0.49
    Activations Density 0.000%

    No Known Activations