© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6703
    Prev
    Next
    INDEX
    Explanations

    citations and programming code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_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
    Ε
    0.60
     vst
    0.55
     перехода
    0.55
     цент
    0.54
     taut
    0.53
     knowledgeable
    0.52
     obtainable
    0.52
     REGI
    0.51
     回転
    0.51
     antica
    0.51
    POSITIVE LOGITS
    ᱑
    0.57
     içinde
    0.56
    athi
    0.55
    lected
    0.54
    who
    0.54
    ใคร
    0.54
    params
    0.53
    leting
    0.52
    Restart
    0.52
    พวก
    0.52
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.