© 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. 15112
    Prev
    Next
    INDEX
    Explanations

    **being suspended**

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

    The neuron fires strongly on numeric or digit‐based tokens (i.e. standalone numbers or number‐like strings).

    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
    älte
    0.87
     كه
    0.82
    ));
    0.77
    artikel
    0.77
    𝐬
    0.74
    صار
    0.73
     acides
    0.73
     Özel
    0.71
     jungen
    0.71
    ٤
    0.70
    POSITIVE LOGITS
     engulf
    0.93
    the
    0.80
    하려고
    0.77
     conjugation
    0.77
    వేయ
    0.77
     thereupon
    0.75
     enshr
    0.75
    斟
    0.75
    ق
    0.73
    ﻟ
    0.73
    Activations Density 0.000%

    No Known Activations