© 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. 2453
    Prev
    Next
    INDEX
    Explanations

    rates, distance, and between

    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
     census
    0.41
    vim
    0.41
    usus
    0.41
    ">
    0.40
    Pricing
    0.40
    ราคา
    0.40
    としての
    0.39
     pricing
    0.38
    #
    0.38
    tain
    0.37
    POSITIVE LOGITS
     tranquille
    0.46
     Rate
    0.43
     mellom
    0.43
     між
    0.42
     tussen
    0.41
     taux
    0.40
     mellem
    0.40
     Between
    0.40
     tenang
    0.40
     cálculo
    0.40
    Activations Density 0.000%

    No Known Activations