© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-262K
    4. 148609
    Prev
    Next
    INDEX
    Explanations

    single-page websites

    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
    setInt
    0.79
    profitable
    0.78
    hurt
    0.76
    separated
    0.75
     ທ
    0.75
     metavar
    0.74
     unprofitable
    0.74
    unable
    0.72
    ่ง
    0.71
     hurtful
    0.71
    POSITIVE LOGITS
     Ste
    0.70
     fe
    0.67
     Component
    0.67
    屐
    0.67
     Graphite
    0.64
     Nix
    0.64
     slow
    0.64
     daí
    0.63
     protocol
    0.63
     grilling
    0.63
    Activations Density 0.001%

    No Known Activations