© 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. 26502
    Prev
    Next
    INDEX
    Explanations

    entire/whole/complete + noun

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

    dataset acquisition

    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
     laisse
    0.52
    钀
    0.51
     laissé
    0.47
    ൧
    0.46
     quieter
    0.45
     pretentious
    0.45
     murderous
    0.44
     quiet
    0.44
    Benzyloxy
    0.44
    ၡ
    0.44
    POSITIVE LOGITS
    izer
    0.50
    uffer
    0.49
    -
    0.44
    Essa
    0.43
    ior
    0.43
    way
    0.43
     Перед
    0.43
     Ответ
    0.42
    az
    0.41
    ya
    0.41
    Activations Density 0.000%

    No Known Activations