Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-65K
    4. 1615
    Prev
    Next
    INDEX
    Explanations

    Mont Blanc, Guava, Eidolon

    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_29_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
      
    0.66
     *
    0.57
     
    0.55
    ,
    0.51
     a
    0.49
    ↵
    0.49
     (
    0.46
    <0xC2>
    0.46
    ↵↵
    0.45
       
    0.44
    POSITIVE LOGITS
    <unused86>
    0.46
    ྥ
    0.46
    goài
    0.46
    abhave
    0.45
    tAux
    0.45
    <unused118>
    0.45
    abhavena
    0.45
    ámenes
    0.45
    <unused36>
    0.45
    estomac
    0.45
    Activations Density 12.558%

    No Known Activations