© 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. 46053
    Prev
    Next
    INDEX
    Explanations

    substance descriptions and purity

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

    noun definitions and uses

    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
    symmetry
    0.51
    religion
    0.49
     میراتھن
    0.48
    estimation
    0.47
    constraints
    0.47
    領域
    0.46
    ฤ
    0.45
    mutex
    0.44
     festgelegt
    0.44
     Zeitraum
    0.43
    POSITIVE LOGITS
     products
    0.51
     slums
    0.50
     daqu
    0.47
     produtos
    0.46
     Herbal
    0.45
     ambulances
    0.44
     obat
    0.43
     usuários
    0.43
     野
    0.43
     atores
    0.42
    Activations Density 0.001%

    No Known Activations