© 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. 11113
    Prev
    Next
    INDEX
    Explanations

    II need

    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
     স্প
    1.33
     бле
    1.31
     拉
    1.27
     Prompt
    1.27
     紫
    1.27
     нау
    1.25
     বৈ
    1.22
    玻
    1.21
     பா
    1.21
     带
    1.21
    POSITIVE LOGITS
     sebagainya
    1.07
     bzw
    1.05
     yoki
    1.04
     usw
    1.03
     atau
    1.02
     svih
    0.99
    തെന്നും
    0.98
    /)
    0.98
     لگانے
    0.98
     (?)
    0.97
    Activations Density 0.017%

    No Known Activations