© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 7497
    Prev
    Next
    INDEX
    Explanations

    similar to constraints

    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_22_width_262k_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
     hom
    0.64
     poh
    0.63
     well
    0.60
    hom
    0.59
     `
    0.58
     weil
    0.58
     rhythm
    0.57
      
    0.57
     responsibility
    0.57
     chain
    0.56
    POSITIVE LOGITS
    setEnabled
    0.78
    ꯟ
    0.77
    Enabled
    0.76
    大气
    0.74
    AsUpIndicator
    0.72
     പറ്റ
    0.72
    ﭥ
    0.72
    럿
    0.71
     ecma
    0.71
    cije
    0.70
    Activations Density 0.000%

    No Known Activations