© 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. 9018
    Prev
    Next
    INDEX
    Explanations

    Meta, Architect, 6, 168

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

    The neuron responds strongly to uncommon or rare single-word tokens (i.e. low-frequency 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
     cycled
    0.74
     客
    0.74
    Servo
    0.73
     九
    0.73
     Laplace
    0.72
     Servo
    0.72
     Campos
    0.71
     Cx
    0.71
     ${\
    0.71
     Serv
    0.70
    POSITIVE LOGITS
    ര്‍
    0.81
    ટી
    0.70
    লিখিত
    0.69
     logement
    0.68
    गौर
    0.67
    iasco
    0.66
     ഒഴി
    0.66
    ูนย์
    0.65
    zés
    0.64
     પહો
    0.64
    Activations Density 0.000%

    No Known Activations