© 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. 34784
    Prev
    Next
    INDEX
    Explanations

    quick fix or historical segments

    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
     derm
    0.50
     retin
    0.50
     Xiaomi
    0.49
     g
    0.47
     substantial
    0.47
     Pokemon
    0.46
     ఏద
    0.45
     l
    0.45
     theſe
    0.44
     pulumi
    0.44
    POSITIVE LOGITS
    domains
    0.55
    apä
    0.54
    är
    0.50
    áu
    0.50
     éd
    0.49
    é
    0.48
    archives
    0.47
    écou
    0.47
    ambique
    0.47
    independent
    0.46
    Activations Density 0.001%

    No Known Activations