© 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. 13-GEMMASCOPE-2-RES-65K
    7. 234
    Prev
    Next
    INDEX
    Explanations

    code structure

    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_13_width_65k_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
    -,
    1.07
     tending
    0.96
     tendency
    0.93
    ’-
    0.91
     penchant
    0.91
    -”
    0.90
     +/-
    0.90
     (+
    0.89
    ²+
    0.88
     tendencies
    0.87
    POSITIVE LOGITS
    <eos>
    1.30
     áng
    0.90
    ऩ
    0.86
     वर्मा
    0.84
    ênd
    0.83
    อย่า
    0.82
    راہ
    0.80
    這樣
    0.80
     yêu
    0.80
    ureka
    0.79
    Activations Density 0.045%

    No Known Activations