© 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. 125383
    Prev
    Next
    INDEX
    Explanations

    action followed by outcome

    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
    ali
    0.52
    ald
    0.48
    quant
    0.48
    exterior
    0.48
    immigration
    0.48
     dumbbells
    0.46
    ')$
    0.46
     exterior
    0.46
    huh
    0.45
     warranties
    0.45
    POSITIVE LOGITS
    ្សែ
    0.50
     SOURCE
    0.46
    繇
    0.45
     REGI
    0.45
    нией
    0.45
    ッセージ
    0.44
     TX
    0.43
     deine
    0.43
    句
    0.43
     región
    0.42
    Activations Density 0.001%

    No Known Activations