© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 25874
    Prev
    Next
    INDEX
    Explanations

    conversational dialogue, future training

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
     ਜਾ
    0.54
    Bracelet
    0.50
     ϒ
    0.49
    stärke
    0.49
     МО
    0.49
     мл
    0.48
    
    0.47
    izadores
    0.47
     შეიძ
    0.47
    வ்வேறு
    0.47
    POSITIVE LOGITS
    ll
    0.49
     CV
    0.46
     expression
    0.46
     Ox
    0.45
     slang
    0.44
    `
    0.44
     Oils
    0.44
     to
    0.43
     Volume
    0.43
     Oracle
    0.43
    Activations Density 0.001%

    No Known Activations