© 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-65K
    7. 1267
    Prev
    Next
    INDEX
    Explanations

    words or names for identification

    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_65k_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
     invál
    0.42
    যাপন
    0.41
     및
    0.40
    ເຮ
    0.40
     infestations
    0.39
     noir
    0.39
    ുകളും
    0.39
     impairments
    0.39
    </td>
    0.38
     abrog
    0.38
    POSITIVE LOGITS
     அடுத்த
    0.53
    Joy
    0.43
    Stephen
    0.42
     Patricia
    0.42
    Carrie
    0.41
     цього
    0.40
     женщины
    0.40
    这一
    0.40
    COTT
    0.40
     Walt
    0.40
    Activations Density 0.001%

    No Known Activations