© 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. 20103
    Prev
    Next
    INDEX
    Explanations

    guppy guppies

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

    dry mop, briefly slipped, timer

    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
     calcite
    0.48
    联动
    0.47
    晔
    0.45
    不喜欢
    0.44
     ACHIE
    0.44
     kính
    0.41
     није
    0.41
    Tidak
    0.41
    ंधरा
    0.40
    实行
    0.40
    POSITIVE LOGITS
    ani
    0.59
    squared
    0.53
    loss
    0.52
    ä
    0.51
     northwestern
    0.50
    down
    0.49
    wright
    0.48
    á
    0.48
    /'
    0.48
    orient
    0.47
    Activations Density 0.000%

    No Known Activations