© 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. 32602
    Prev
    Next
    INDEX
    Explanations

    parenthetical phrases, numbers, or certain words

    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
     시즌
    0.47
    ؟
    0.41
    AUD
    0.41
    ？
    0.41
    ון
    0.41
    ᱗
    0.40
    ?>
    0.40
    訊
    0.39
    ᱙
    0.39
     आर्थिक
    0.38
    POSITIVE LOGITS
     purposes
    0.46
     wiederum
    0.42
     determin
    0.41
     funz
    0.39
     lavender
    0.39
     seamlessly
    0.38
     तब्
    0.38
     empêcher
    0.38
     recop
    0.38
     afin
    0.38
    Activations Density 0.001%

    No Known Activations