© 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. 86439
    Prev
    Next
    INDEX
    Explanations

    money, finance, or security terms

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

    noun followed by punctuation or short word

    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
    lineEdit
    0.46
    =(
    0.45
    '=
    0.45
    est
    0.44
    畢業
    0.43
     COLLATE
    0.43
     prestigious
    0.43
    =
    0.43
    erview
    0.40
    జాగా
    0.40
    POSITIVE LOGITS
     abhäng
    0.50
     подход
    0.49
    恸
    0.49
     airflow
    0.47
    тном
    0.46
     atmosph
    0.45
     típus
    0.45
     ней
    0.45
     फ्लू
    0.44
     neuropath
    0.44
    Activations Density 0.000%

    No Known Activations