© 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
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 13218
    Prev
    Next
    INDEX
    Explanations

    🔥 and honey

    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
    s
    2.50
    debian
    2.14
    ات
    2.00
    8
    1.95
    9
    1.93
     نقدم
    1.81
    '
    1.76
    7
    1.73
    usercontent
    1.72
    me
    1.68
    POSITIVE LOGITS
    Ⴚ
    2.48
    ObjectHideFlags
    2.47
     rapidement
    2.43
    𝕕
    2.41
    𝕖
    2.37
    ExpNow
    2.36
    गिंग
    2.36
    者の
    2.33
    
    2.33
    
    2.31
    Activations Density 0.029%

    No Known Activations