© 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. 8090
    Prev
    Next
    INDEX
    Explanations

    The neuron detects numeric quantities and measurements (e.g., counts, durations, daily rates).

    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
    ви
    1.14
    ور
    1.11
    $$_
    1.05
    ست
    1.04
    ول
    0.99
    па
    0.98
    أ
    0.97
    أن
    0.96
    دا
    0.94
     Preparation
    0.93
    POSITIVE LOGITS
    day
    1.43
    मर्रा
    1.28
    s
    1.26
    마다
    1.23
    OfWeek
    1.23
    々と
    1.22
    ವೂ
    1.22
    r
    1.21
     발생하는
    1.20
    ל
    1.20
    Activations Density 5.254%

    No Known Activations