© 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. 135376
    Prev
    Next
    INDEX
    Explanations

    financial transactions and outcomes

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

    code blocks with punctuation and special characters

    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
     زاده
    0.46
     Beaux
    0.46
     Joan
    0.43
     Zell
    0.43
     Gall
    0.43
     Monaco
    0.42
     Bowling
    0.42
     B
    0.42
     Brooklyn
    0.41
     Blazer
    0.41
    POSITIVE LOGITS
     iterated
    0.47
     dosimetry
    0.46
     avaliar
    0.46
     mainten
    0.46
     relativo
    0.46
     imprint
    0.46
     monotony
    0.45
     imperme
    0.45
     profilo
    0.45
     unclear
    0.45
    Activations Density 0.000%

    No Known Activations