© 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. 14261
    Prev
    Next
    INDEX
    Explanations

    cored, peeled, sliced apples

    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
     বিমানের
    1.29
    ත්‍ර
    1.26
     कब्रिस्तान
    1.20
     больных
    1.19
    疃
    1.16
     नॉर्थ
    1.15
     території
    1.13
     હજાર
    1.13
    丏
    1.13
     samoglas
    1.12
    POSITIVE LOGITS
     tough
    1.09
    <0x0D>
    1.07
     innovative
    1.03
    newblock
    1.00
    )</
    0.99
     sophisticated
    0.99
     Puja
    0.98
     nurturing
    0.97
     lovely
    0.97
     excellent
    0.96
    Activations Density 0.001%

    No Known Activations