© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 7982
    Prev
    Next
    INDEX
    Explanations

    Numbers followed by years

    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
    ->"
    2.71
    শতঃ
    2.39
    %","
    2.34
    цу
    2.33
    FindFirst
    2.18
    ()["
    2.13
    𝐜
    2.12
    𝐧
    2.09
    rank
    2.05
    𝐥
    2.05
    POSITIVE LOGITS
     ‘
    2.40
    া
    2.33
     ทํา
    2.26
    ］
    2.21
     สํา
    2.15
    ebel
    2.14
    সই
    2.14
    …’
    2.09
    ष्‍ट्र
    2.07
     คํา
    2.05
    Activations Density 0.269%

    No Known Activations