© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 11604
    Prev
    Next
    INDEX
    Explanations

    action verbs for tasks and capabilities

    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
    ,[
    0.48
    ס
    0.47
    fabric
    0.45
     Пример
    0.45
    ק
    0.45
    acier
    0.44
    י
    0.44
    ambil
    0.43
    <0x80>
    0.43
     {
    0.43
    POSITIVE LOGITS
     yourself
    0.69
     yourselves
    0.64
    ings
    0.63
    able
    0.61
    ینگ
    0.59
    者が
    0.59
     Yourself
    0.56
    ってください
    0.55
     বলো
    0.53
    iveness
    0.52
    Activations Density 0.261%

    No Known Activations