© 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. 31-GEMMASCOPE-2-RES-16K
    7. 3190
    Prev
    Next
    INDEX
    Explanations

    established entities or systems

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

    The neuron activates on numeric tokens—particularly measurements, decimal numbers, and other digit-based data.

    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_31_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
    ?
    1.09
     queremos
    0.96
    0.95
    !
    0.95
     our
    0.94
    ?!
    0.88
     tady
    0.87
     you
    0.86
     vores
    0.85
     tienes
    0.84
    POSITIVE LOGITS
     автоматлары
    0.98
    <unused2152>
    0.95
    ቈ
    0.82
    <unused2173>
    0.82
    <unused2148>
    0.78
    <unused2121>
    0.74
    <unused2172>
    0.74
    <unused136>
    0.72
     መድሃኒ
    0.72
    <unused184>
    0.71
    Activations Density 0.135%

    No Known Activations