© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 5949
    Prev
    Next
    INDEX
    Explanations

    generating different examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
     inasmuch
    1.04
     while
    0.97
     tandis
    0.94
    与此同时
    0.92
     those
    0.90
     virtud
    0.90
     too
    0.90
    孖
    0.89
     last
    0.88
    少了
    0.87
    POSITIVE LOGITS
    0
    2.28
     verschillende
    2.26
     forskjellige
    2.24
     verschiedene
    2.21
     different
    2.20
     olika
    2.19
     nationalities
    2.19
    異なる
    2.17
    different
    2.11
     diferentes
    2.11
    Activations Density 0.217%

    No Known Activations