© 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. 13699
    Prev
    Next
    INDEX
    Explanations

    physical states and conditions

    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
    鲞
    0.50
    <0x89>
    0.48
    
    0.47
    <0x86>
    0.45
    ᱴ
    0.44
    idamente
    0.43
    rió
    0.42
    alarında
    0.41
     नामों
    0.41
    榄
    0.41
    POSITIVE LOGITS
     بعد
    0.66
     after
    0.63
     після
    0.60
     Tired
    0.60
    จากการ
    0.56
     despite
    0.56
     dopo
    0.55
     tired
    0.55
     após
    0.55
     setelah
    0.54
    Activations Density 0.053%

    No Known Activations