© 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. 2781
    Prev
    Next
    INDEX
    Explanations

    print on demand

    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
    pectral
    1.39
    ijas
    1.25
    答
    1.25
     quoted
    1.25
     venons
    1.24
     outra
    1.22
    惴
    1.22
     آئینہ
    1.21
    waj
    1.19
     altri
    1.19
    POSITIVE LOGITS
    llo
    1.56
    lon
    1.51
    lai
    1.41
    서
    1.38
    mäßig
    1.36
    
    1.34
    犸
    1.32
    Permalink
    1.30
    lara
    1.30
    lif
    1.28
    Activations Density 0.000%

    No Known Activations