© 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. 24554
    Prev
    Next
    INDEX
    Explanations

    dollar amounts or possessions

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

    customers browse

    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
     ചാ
    0.49
     überall
    0.49
     急
    0.49
     diesem
    0.48
     Länder
    0.48
     లక్ష
    0.48
     här
    0.46
    rean
    0.46
     textiles
    0.46
    赸
    0.46
    POSITIVE LOGITS
    ('/')
    0.46
    DA
    0.42
    ҳои
    0.42
    全ての
    0.42
    https
    0.42
    ("/")
    0.41
    ای
    0.40
     majesty
    0.40
    अभिने
    0.40
     ouvir
    0.39
    Activations Density 0.000%

    No Known Activations