© 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. 7-GEMMASCOPE-2-RES-16K
    7. 11501
    Prev
    Next
    INDEX
    Explanations

    a followed by descriptive term

    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_7_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
    া
    3.28
    ۰
    3.00
    a
    2.97
    i
    2.86
    ্ণ
    2.67
    ه
    2.65
    immung
    2.59
    otopy
    2.58
    ्रपान
    2.57
    NUMX
    2.48
    POSITIVE LOGITS
    AWSJavaScriptSDK
    3.75
    affold
    2.86
    attered
    2.85
    ggbb
    2.84
     covering
    2.82
    
    2.75
     verbo
    2.75
     literals
    2.75
    ঙ্কর
    2.73
    睺
    2.66
    Activations Density 0.047%

    No Known Activations