© 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-65K
    7. 368
    Prev
    Next
    INDEX
    Explanations

    spreads through/into, varies greatly/significantly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_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
     C
    0.81
    C
    0.81
     L
    0.79
     A
    0.78
    0.74
    A
    0.74
      
    0.73
     B
    0.72
     T
    0.71
    T
    0.70
    POSITIVE LOGITS
    <unused801>
    1.59
    <unused1465>
    1.57
    <unused1440>
    1.56
    <unused842>
    1.54
    𒆝
    1.53
    <unused1288>
    1.53
    Polynucleaires
    1.53
    VSTYPE
    1.53
    <unused79>
    1.52
    ꗫ
    1.52
    Activations Density 0.971%

    No Known Activations