© 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. 165951
    Prev
    Next
    INDEX
    Explanations

    followed by

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

    basic to advanced

    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
     sortir
    0.50
     sozinha
    0.49
     figura
    0.47
     músicas
    0.46
     numai
    0.46
     occasionally
    0.45
    ⵚ
    0.45
    Wires
    0.45
    િયાન
    0.44
     タイプ
    0.44
    POSITIVE LOGITS
    meer
    0.46
     接
    0.42
     เขา
    0.41
    >..\
    0.41
     کہتے
    0.41
    地に
    0.41
     شدن
    0.41
     Meer
    0.39
    Addressing
    0.39
    鈔
    0.38
    Activations Density 0.000%

    No Known Activations