© 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. 31-GEMMASCOPE-2-RES-65K
    4. 8052
    Prev
    Next
    INDEX
    Explanations

    cracked sound, concentrated prey, Sun, Man Tiber, Clicking status

    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
     یق
    0.44
     সত্যিই
    0.42
    ຖືກ
    0.41
     лов
    0.41
    пли
    0.40
    
    0.40
    βολ
    0.39
    icyclic
    0.39
    ],[
    0.39
     Bhi
    0.39
    POSITIVE LOGITS
     museum
    0.45
     gemeente
    0.43
     Macrom
    0.42
     photographers
    0.41
     an
    0.41
     org
    0.40
     uma
    0.39
     bestuur
    0.39
     wireless
    0.39
     communic
    0.38
    Activations Density 0.023%

    No Known Activations