© 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. 16406
    Prev
    Next
    INDEX
    Explanations

    favorably influences or affects

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

    finance and data analysis

    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
    chosen
    0.57
     millón
    0.54
     І
    0.49
     Mendez
    0.47
     ingreso
    0.47
     pér
    0.47
     Є
    0.46
     tých
    0.46
    Ḵ
    0.46
     conjunto
    0.46
    POSITIVE LOGITS
    灼
    0.46
    propylene
    0.43
     స్టార్
    0.43
     ذریع
    0.42
    өг
    0.41
     Timing
    0.41
    Timing
    0.41
    qa
    0.40
    时
    0.40
    染色
    0.40
    Activations Density 0.000%

    No Known Activations