© 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. 24-GEMMASCOPE-2-RES-16K
    7. 11528
    Prev
    Next
    INDEX
    Explanations

    software, 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_24_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
    ksjon
    0.77
    (
    0.76
    circa
    0.75
     fosse
    0.75
    sized
    0.74
    cation
    0.74
    iskt
    0.70
     kohta
    0.70
    tumor
    0.70
    g
    0.70
    POSITIVE LOGITS
    সাধারণ
    0.79
    ྒྱ
    0.78
     বিক্রয়
    0.76
     afar
    0.74
     Peas
    0.74
     Software
    0.73
    志
    0.73
     Sketches
    0.72
     Estates
    0.71
     Symbols
    0.71
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.