© 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. 40288
    Prev
    Next
    INDEX
    Explanations

    sorting, closets, planning, TikTok, checks

    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
     scrot
    0.46
     पनि
    0.46
     oppure
    0.45
     superhero
    0.45
     合
    0.45
    睾
    0.44
     või
    0.44
     jika
    0.43
     acetaminophen
    0.43
     dystopian
    0.43
    POSITIVE LOGITS
    ary
    0.47
    Forbes
    0.46
     breezes
    0.46
    ienz
    0.46
    ward
    0.45
    amad
    0.45
    ang
    0.45
    drawer
    0.44
     crews
    0.44
    W
    0.44
    Activations Density 0.001%

    No Known Activations