© 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. 29-GEMMASCOPE-2-RES-262K
    7. 148957
    Prev
    Next
    INDEX
    Explanations

    sys/ includes

    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_29_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
     diamante
    0.74
    elligence
    0.73
     vote
    0.71
    Titan
    0.70
     rotations
    0.69
     armature
    0.69
    ਐ
    0.68
     misalkan
    0.68
     rotates
    0.68
    searchview
    0.68
    POSITIVE LOGITS
    製作
    0.75
     bert
    0.68
    
    0.66
    त्रा
    0.64
     দৈনিক
    0.64
    omi
    0.63
    댓
    0.62
    ATTA
    0.61
     کھی
    0.60
    ᱽ
    0.60
    Activations Density 0.001%

    No Known Activations