© 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. 2519
    Prev
    Next
    INDEX
    Explanations

    father's son

    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
    e
    1.66
    a
    1.34
     yearling
    1.18
    ास
    1.18
     тера
    1.18
    热
    1.16
    epe
    1.15
     tecnica
    1.15
    疾患
    1.15
    Me
    1.15
    POSITIVE LOGITS
     Betting
    1.54
    נן
    1.37
    OrElse
    1.37
    andang
    1.36
    رحب
    1.34
     dealings
    1.32
     `>`,
    1.31
    十六章
    1.30
    θυν
    1.29
    קר
    1.28
    Activations Density 0.000%

    No Known Activations