© 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. 15266
    Prev
    Next
    INDEX
    Explanations

    other communities or states

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

    competitor and similar comparison

    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
     が
    0.43
    quez
    0.43
    datei
    0.42
    kez
    0.41
    dat
    0.41
    原有
    0.40
    monte
    0.40
    喋
    0.40
    addTo
    0.40
    descripcion
    0.40
    POSITIVE LOGITS
     neighboring
    0.66
     competitor
    0.64
     comparable
    0.64
     similar
    0.63
     competitors
    0.62
     rivals
    0.62
     유사
    0.62
     comparator
    0.61
     peers
    0.61
     similares
    0.60
    Activations Density 0.103%

    No Known Activations