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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 15-GEMMASCOPE-2-RES-262K
    7. 69324
    Prev
    Next
    INDEX
    Explanations

    exceptional customer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_15_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
     continuance
    1.18
     perplexed
    1.13
     craze
    1.06
     frowned
    1.05
     dissidents
    1.05
     Restriction
    1.05
    逡
    1.05
     hesitated
    1.05
     ă
    1.03
    넥
    1.03
    POSITIVE LOGITS
    *(
    1.77
    两次
    1.57
    garbage
    1.57
    #$%
    1.55
    *"
    1.55
    written
    1.51
    *-
    1.48
    mocha
    1.47
     mago
    1.47
     $%
    1.46
    Activations Density 0.003%

    No Known Activations