© 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. 2764
    Prev
    Next
    INDEX
    Explanations

    детали

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron flags tokens written in Cyrillic script (i.e. Russian words).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    Especific
    0.71
    és
    0.68
    WASHINGTON
    0.67
    Teste
    0.66
    蟶
    0.64
    ୈ
    0.64
    이션
    0.63
    Gé
    0.63
    Transcript
    0.62
    minutes
    0.61
    POSITIVE LOGITS
     этого
    0.85
     и
    0.80
     по
    0.79
     сегодняш
    0.79
     của
    0.79
     нашего
    0.78
     τῶν
    0.78
     самого
    0.75
     самих
    0.74
     одного
    0.74
    Activations Density 0.001%

    No Known Activations