© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 17857
    Prev
    Next
    INDEX
    Explanations

    currency amounts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gaussian
    0.44
     Browser
    0.42
     homogeneous
    0.42
    andom
    0.41
    )]^{
    0.41
    Browser
    0.40
     Chromatography
    0.39
    层
    0.39
     ópt
    0.38
    螟
    0.38
    POSITIVE LOGITS
     dollars
    1.29
    dollars
    1.05
     Dollars
    1.03
     долларов
    0.98
     dollari
    0.97
     $
    0.96
     euros
    0.94
     ($
    0.93
     dollar
    0.92
     USD
    0.91
    Activations Density 0.014%

    No Known Activations