© 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. 45072
    Prev
    Next
    INDEX
    Explanations

    US place abbreviations

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

    natural subordinate itself

    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
     परियोजनाओं
    0.45
     (†
    0.45
     IUnary
    0.45
     zarówno
    0.43
     projects
    0.42
     Floors
    0.42
     '../../
    0.42
    1
    0.42
    8
    0.41
     Projects
    0.41
    POSITIVE LOGITS
     अंब
    0.47
     अम्ब
    0.47
    宻
    0.44
    фу
    0.43
    нце
    0.42
     θεω
    0.42
     ाट
    0.41
     цену
    0.41
    foe
    0.41
    нку
    0.40
    Activations Density 0.000%

    No Known Activations