© 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-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 13480
    Prev
    Next
    INDEX
    Explanations

    introducing well,

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    𐰼
    1.74
    湿度
    1.71
    ㄌ
    1.64
    ᚗ
    1.61
    𐰆
    1.60
     regalo
    1.57
     remboursement
    1.56
    CCNC
    1.56
    樎
    1.56
     terceros
    1.55
    POSITIVE LOGITS
     guess
    1.11
     rank
    1.06
    rank
    1.06
     kenn
    1.01
    pp
    1.00
     ‘
    1.00
     fla
    0.96
     hostile
    0.96
     crushed
    0.95
    ڑوں
    0.93
    Activations Density 0.051%

    No Known Activations