© 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. 106589
    Prev
    Next
    INDEX
    Explanations

    names, email addresses, credentials

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

    past and future context

    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
     寝
    0.50
     zusätzliche
    0.50
    ForSettings
    0.49
     ovipares
    0.49
    ピー
    0.48
     истории
    0.48
    Einstellungen
    0.48
     дочери
    0.47
     accueille
    0.47
    ْر
    0.46
    POSITIVE LOGITS
    ial
    0.53
    ↵
    0.50
    0.48
    if
    0.47
    rm
    0.46
     that
    0.45
     Width
    0.45
    all
    0.43
    ell
    0.43
     it
    0.42
    Activations Density 0.001%

    No Known Activations