© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 8906
    Prev
    Next
    INDEX
    Explanations

    software development instructions

    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
    ারন
    0.81
    Ꮏ
    0.80
    hiy
    0.78
    irdiği
    0.77
    unii
    0.77
    arı
    0.76
    abaya
    0.75
    iert
    0.75
    ißler
    0.75
    újt
    0.74
    POSITIVE LOGITS
     Mysterious
    0.75
     Dark
    0.72
     wasp
    0.71
     tip
    0.70
     cylindrical
    0.70
     pathogen
    0.69
     (%)
    0.69
     reign
    0.68
     Ceramic
    0.68
     Cameroon
    0.68
    Activations Density 0.336%

    No Known Activations