© 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. 1434
    Prev
    Next
    INDEX
    Explanations

    everything from

    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
    ن
    1.08
    ков
    0.99
    DAT
    0.99
    Daniels
    0.99
    Defs
    0.98
    ের
    0.97
    ER
    0.97
     φορ
    0.97
    Directors
    0.97
    cA
    0.96
    POSITIVE LOGITS
     else
    1.27
     άλλο
    1.03
     muhimu
    1.01
     אחר
    0.95
     juridique
    0.93
    ي
    0.92
     annat
    0.90
    }}^{
    0.89
     apie
    0.89
    り
    0.89
    Activations Density 0.138%

    No Known Activations