© 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. 31-GEMMASCOPE-2-RES-262K
    7. 26940
    Prev
    Next
    INDEX
    Explanations

    numbers with units of time or measurement

    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_31_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
     ACTION
    0.45
     for
    0.44
    %
    0.41
     বছরে
    0.40
     cah
    0.39
     GAN
    0.38
     FAQ
    0.38
     ALL
    0.37
    াত্য
    0.37
     chunk
    0.36
    POSITIVE LOGITS
    lois
    0.44
    尼斯
    0.44
     기다
    0.41
     особенностей
    0.40
    ┉
    0.40
     препят
    0.39
     ہوئی۔
    0.39
    ীন্দ্র
    0.39
    에서
    0.39
    න්ත
    0.38
    Activations Density 0.030%

    No Known Activations