© 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. 200397
    Prev
    Next
    INDEX
    Explanations

    container, fixture, placeholder, table cell

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

    investigate the circumstances

    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
     criando
    0.52
    臉
    0.51
     izbor
    0.50
    ע
    0.49
     SAND
    0.49
     rechaz
    0.49
     oblik
    0.49
     kuat
    0.48
    茉
    0.48
    強い
    0.47
    POSITIVE LOGITS
    Container
    0.52
    TERS
    0.52
     identifies
    0.49
    Fixture
    0.47
    cene
    0.47
    Suggest
    0.46
    TableCell
    0.46
    UpperCase
    0.45
    Placeholder
    0.45
    uggest
    0.45
    Activations Density 0.000%

    No Known Activations