© 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. 240050
    Prev
    Next
    INDEX
    Explanations

    alternative cheeses, corporate strategy, dancers

    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
     Venetian
    0.52
     Marshal
    0.52
     Cuban
    0.51
     War
    0.50
     Uy
    0.50
    -
    0.47
    स्तिष्क
    0.46
     rustic
    0.45
     Phosph
    0.44
     died
    0.43
    POSITIVE LOGITS
    ESI
    0.54
     efficaces
    0.52
    น
    0.52
    FAM
    0.51
    茗
    0.48
     комплекс
    0.46
    ILE
    0.46
    PACE
    0.46
     immédi
    0.46
     mơ
    0.46
    Activations Density 0.000%

    No Known Activations