© 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. 40-GEMMASCOPE-2-RES-262K
    4. 98972
    Prev
    Next
    INDEX
    Explanations

    cat or cats

    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_40_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
     напо
    0.39
    緝
    0.39
    詿
    0.38
    óc
    0.38
     Diện
    0.38
     প্রাস
    0.37
     SUCH
    0.37
    <unused2028>
    0.36
     AG
    0.36
     PLUS
    0.36
    POSITIVE LOGITS
    CAT
    0.66
     CAT
    0.62
     catamaran
    0.56
    Cat
    0.53
    categ
    0.52
     feline
    0.52
     cathodes
    0.50
    cata
    0.50
     cate
    0.49
     Cat
    0.48
    Activations Density 0.022%

    No Known Activations