© 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. 4151
    Prev
    Next
    INDEX
    Explanations

    FPS, RAM,

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

    The neuron is triggered by numeric tokens, i.e. it identifies numbers or numeric measurements in the text.

    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
    норий
    0.72
    ٿ
    0.68
    LOTREntity
    0.66
    知らない
    0.65
    oclaw
    0.64
    hanahu
    0.63
    PickerDialog
    0.61
     nende
    0.61
     ગામ
    0.60
    তনা
    0.60
    POSITIVE LOGITS
     while
    0.91
    .
    0.85
     mentre
    0.80
     estándar
    0.77
     மற்றும்
    0.77
    -
    0.75
     whilst
    0.74
     with
    0.73
     với
    0.70
     While
    0.69
    Activations Density 0.463%

    No Known Activations