© 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. 127714
    Prev
    Next
    INDEX
    Explanations

    quantifiable financial transactions

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

    prepayment, differences, sends

    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
    ૮
    0.55
    schod
    0.51
     постоянно
    0.48
    ících
    0.48
     обо
    0.46
     जॉर्ज
    0.46
     чрез
    0.46
     спря
    0.46
    encja
    0.46
    ния
    0.46
    POSITIVE LOGITS
     pho
    0.52
     replicated
    0.48
    MET
    0.46
     hypothesized
    0.46
     `"
    0.44
    =\
    0.43
     ignore
    0.43
     contributed
    0.43
     reacted
    0.42
     nicotine
    0.42
    Activations Density 0.000%

    No Known Activations