© 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. 12431
    Prev
    Next
    INDEX
    Explanations

    language examples

    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
    0
    1.23
    7
    1.02
    6
    1.02
    2
    0.93
    1
    0.90
    4
    0.88
    5
    0.84
    9
    0.83
    3
    0.82
    (),
    0.77
    POSITIVE LOGITS
     akses
    0.83
     bersifat
    0.83
     gelişt
    0.79
     verlei
    0.79
     informações
    0.78
     uzman
    0.77
     الاطلاع
    0.77
     acess
    0.76
     inj
    0.75
     dobra
    0.75
    Activations Density 0.000%

    No Known Activations