© 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. 2807
    Prev
    Next
    INDEX
    Explanations

    public static void main(String[] args)

    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
     bleeding
    1.92
     organ
    1.89
    წყვე
    1.86
     élo
    1.82
    𝔻
    1.81
     bear
    1.81
     pono
    1.80
    டி
    1.79
    btc
    1.77
    prüng
    1.76
    POSITIVE LOGITS
    ാ
    2.22
    Tokenizer
    2.18
    चीन
    2.07
    ળી
    2.04
    ා
    2.03
    тті
    1.97
    tolower
    1.95
    toupper
    1.95
    IsNullOrEmpty
    1.95
    Highlight
    1.91
    Activations Density 0.006%

    No Known Activations