© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 7666
    Prev
    Next
    INDEX
    Explanations

    prestigious individual, found remains

    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_16k_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
     gdyż
    1.15
    टू
    1.11
    ক্ষ
    1.10
    ť
    1.06
     sababu
    1.02
    并将
    1.01
     sebab
    1.00
    ביל
    0.99
    amis
    0.99
     पसर
    0.99
    POSITIVE LOGITS
    ertation
    1.47
     comprehensive
    1.46
     Ν
    1.46
     UVA
    1.46
     PP
    1.45
     cosmopolitan
    1.43
     Pp
    1.41
     geographical
    1.40
    ITARY
    1.39
     EW
    1.39
    Activations Density 0.000%

    No Known Activations