© 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. 122702
    Prev
    Next
    INDEX
    Explanations

    granted certiorari, intuitive healthcare, embroidered logo

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

    EASD abbreviation formatting

    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
    सुबह
    0.60
     articoli
    0.58
     trasporto
    0.53
     sempurna
    0.52
     puncak
    0.52
    ﻱ
    0.52
    ᄈ
    0.52
     poiché
    0.52
    loadNpm
    0.52
     muebles
    0.50
    POSITIVE LOGITS
    aff
    0.49
    .
    0.48
    Generic
    0.47
    System
    0.47
    affer
    0.47
    اف
    0.45
    Software
    0.45
    algorithms
    0.45
    т
    0.45
    Diagnostics
    0.44
    Activations Density 0.000%

    No Known Activations