© 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. 16631
    Prev
    Next
    INDEX
    Explanations

    agent only

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

    subject and outcome description

    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
    னே
    0.53
     reiniciar
    0.52
     secteurs
    0.50
    狮
    0.49
     comunidades
    0.48
     estadísticas
    0.48
    ன்களை
    0.47
    م
    0.47
    једина
    0.47
     sektor
    0.47
    POSITIVE LOGITS
    pi
    0.46
    cos
    0.46
    arms
    0.46
    :
    0.45
    ryt
    0.45
    iotsitewise
    0.44
    ：
    0.44
    nope
    0.44
    chen
    0.43
    zw
    0.43
    Activations Density 0.000%

    No Known Activations