© 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. 46355
    Prev
    Next
    INDEX
    Explanations

    adjectives preceding nouns

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

    weekly digest

    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
    Actress
    0.51
    ریض
    0.50
    cèle
    0.50
    Muito
    0.49
    ريض
    0.48
    profitLoss
    0.46
    Portale
    0.46
    醇
    0.46
    丶
    0.46
    RelativeTo
    0.44
    POSITIVE LOGITS
    vio
    0.48
     ತೆಗೆ
    0.47
    an
    0.46
     but
    0.46
     mening
    0.45
     eruption
    0.45
     leak
    0.44
    anos
    0.44
    ?
    0.44
     আদর্শ
    0.42
    Activations Density 0.000%

    No Known Activations