© 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. 100975
    Prev
    Next
    INDEX
    Explanations

    source attribution in URLs

    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
    จ
    0.47
     neuesten
    0.43
    ให้
    0.43
    যা
    0.42
    Ύ
    0.42
    вли
    0.42
    ElementName
    0.42
    釣り
    0.42
    ท่า
    0.41
    ท่าน
    0.41
    POSITIVE LOGITS
    ode
    0.53
    nia
    0.46
    nab
    0.44
    ફેદ
    0.43
    ken
    0.42
    urry
    0.42
    anym
    0.42
     المناطق
    0.41
    篡
    0.41
    ab
    0.41
    Activations Density 0.001%

    No Known Activations