© 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. 134121
    Prev
    Next
    INDEX
    Explanations

    to join, to stay, Fathers Day

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

    explaining, defining, or describing

    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
    ach
    0.51
    น
    0.50
    am
    0.50
    ocal
    0.48
    agement
    0.47
    CI
    0.46
    ichier
    0.46
    ak
    0.46
    +$
    0.45
    In
    0.45
    POSITIVE LOGITS
     гале
    0.53
    ⋘
    0.53
     sulfon
    0.52
     любо
    0.52
    ▆
    0.52
     анализа
    0.51
     Му
    0.51
    !]
    0.51
     подвод
    0.50
     Harlan
    0.50
    Activations Density 0.000%

    No Known Activations