© 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. 48758
    Prev
    Next
    INDEX
    Explanations

    tax expense, thanks sir, Hamas

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

    fraudulent activities

    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
    rah
    0.48
    apa
    0.47
    ero
    0.47
    —
    0.46
     Colored
    0.44
    colored
    0.43
     ಅವನ
    0.43
     Pos
    0.42
    tez
    0.42
    ean
    0.42
    POSITIVE LOGITS
     budaya
    0.52
    एम
    0.49
    ম
    0.49
    Namun
    0.49
     jambes
    0.46
    Prova
    0.46
    Quando
    0.46
    ГУ
    0.45
    தமாக
    0.45
    Compare
    0.44
    Activations Density 0.000%

    No Known Activations