© 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
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 6798
    Prev
    Next
    INDEX
    Explanations

    post-token words

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

    This neuron activates on isolated numeric tokens—especially decimal numbers—indicating it’s detecting stray floating-point number strings 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_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
    }
    1.14
    		
    1.09
    _
    1.05
    	
    1.05
     =
    1.02
    )
    1.02
    ();
    1.00
    ))
    0.96
    ()
    0.95
    ())
    0.95
    POSITIVE LOGITS
     ferocious
    0.96
     vehement
    0.92
     fomentar
    0.91
     Capcom
    0.90
     paltry
    0.90
     Ryanair
    0.90
     lucrative
    0.89
     dilapidated
    0.88
     Amerika
    0.88
     Aéroport
    0.88
    Activations Density 0.000%

    No Known Activations