© 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. 2401
    Prev
    Next
    INDEX
    Explanations

    technical terms followed by punctuation

    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
    ක්
    2.38
    ểm
    2.37
    로그
    2.32
    ن
    2.30
    aan
    2.29
    upa
    2.29
    ਤਾ
    2.27
    जफ्फर
    2.26
    蚪
    2.24
    상
    2.22
    POSITIVE LOGITS
    uncie
    2.81
    ellan
    2.78
     embr
    2.65
     CGRect
    2.58
     aneu
    2.56
     FRAN
    2.47
    
    2.45
    BED
    2.44
     BRAD
    2.42
    லாத
    2.41
    Activations Density 0.015%

    No Known Activations