© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 612
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_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
    <unused1040>
    1.60
    𒄐
    1.58
    <start_of_turn>
    1.54
    <unused832>
    1.53
    <unused11>
    1.52
    <unused828>
    1.52
    䟝
    1.51
    <unused1237>
    1.50
    <unused1236>
    1.49
    <unused46>
    1.49
    POSITIVE LOGITS
     (
    1.12
    1
    1.03
    (
    0.99
      
    0.98
       
    0.91
    3
    0.85
    2
    0.84
     ,
    0.79
    Z
    0.76
    ,
    0.76
    Activations Density 4.281%

    No Known Activations