© 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. 113057
    Prev
    Next
    INDEX
    Explanations

    Cat Pose, text understanding

    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
    ደን
    0.50
     klant
    0.48
    েরই
    0.48
    琮
    0.47
    ьому
    0.44
     efet
    0.43
    จทย์
    0.42
    禟
    0.42
    BURG
    0.42
    τερα
    0.41
    POSITIVE LOGITS
    ្នក
    0.47
    ulk
    0.46
    ruct
    0.45
    uce
    0.45
     Metabolic
    0.45
    recogn
    0.45
    example
    0.45
    merge
    0.45
    read
    0.44
    ace
    0.44
    Activations Density 0.001%

    No Known Activations