© 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-65K
    7. 20343
    Prev
    Next
    INDEX
    Explanations

    moving beyond

    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_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
    seekers
    0.50
    following
    0.49
     galle
    0.44
    ުޅ
    0.44
    pictures
    0.44
    েরই
    0.43
    า
    0.43
    वान
    0.43
    اين
    0.42
    ене
    0.42
    POSITIVE LOGITS
     AsyncTask
    0.52
     dessas
    0.46
     Alemanha
    0.46
     Fight
    0.45
     मित
    0.45
     Milk
    0.44
    銠
    0.44
     Ton
    0.43
     Brasileiro
    0.43
     Chiến
    0.42
    Activations Density 0.007%

    No Known Activations