© 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. 20280
    Prev
    Next
    INDEX
    Explanations

    RAINN and AI/robotics acronyms

    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
    刘
    0.41
     Aix
    0.41
     Außerdem
    0.40
     macam
    0.39
    പാട്
    0.39
     Sebab
    0.38
    赅
    0.38
     yaklaşık
    0.38
     Ayrıca
    0.38
    犹
    0.38
    POSITIVE LOGITS
    un
    0.46
    ow
    0.44
    il
    0.41
    op
    0.37
    us
    0.36
    ip
    0.36
    cake
    0.36
    6
    0.36
    igh
    0.36
    err
    0.36
    Activations Density 0.041%

    No Known Activations