© 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-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 14846
    Prev
    Next
    INDEX
    Explanations

    by author name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_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
    Kami
    1.25
    ✬
    1.25
     Shroff
    1.24
    Madonna
    1.23
     ഉത്സ
    1.22
     Roshelle
    1.21
     thisobject
    1.20
    槙
    1.19
    
    1.19
    chromiumfx
    1.18
    POSITIVE LOGITS
      
    0.81
    -
    0.77
    ↵
    0.76
     John
    0.71
     trailing
    0.70
    ための
    0.67
     underpinning
    0.66
     using
    0.66
    在
    0.66
     Charles
    0.64
    Activations Density 0.001%

    No Known Activations