© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 79974
    Prev
    Next
    INDEX
    Explanations

    android layout width assignment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     each
    -1.15
    olympic
    -1.09
     uhr
    -1.09
    yyj
    -1.05
    ’:
    -1.05
    pneu
    -1.04
     gavetas
    -1.04
     have
    -1.03
    cartera
    -0.99
    Each
    -0.98
    POSITIVE LOGITS
     is
    1.02
    is
    1.00
    厢
    0.99
     frontiers
    0.98
    Caprio
    0.98
    urtstag
    0.97
    zná
    0.96
    U
    0.94
    Trax
    0.93
     reborn
    0.93
    Activations Density 0.002%

    No Known Activations