© 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. 50541
    Prev
    Next
    INDEX
    Explanations

    list items and configurations

    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
     wrecked
    0.56
    败
    0.51
     crumb
    0.45
     poisoned
    0.43
     wreck
    0.43
    )，
    0.43
    培
    0.42
     thwarted
    0.42
     बिगड़
    0.41
     comest
    0.40
    POSITIVE LOGITS
    enemy
    0.54
    iß
    0.53
    extensions
    0.52
    motorbike
    0.51
    <0x0B>
    0.51
    savvy
    0.50
     Sơn
    0.49
     Chuk
    0.49
    send
    0.49
    ské
    0.49
    Activations Density 0.002%

    No Known Activations