© 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. 2833
    Prev
    Next
    INDEX
    Explanations

    email addresses

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

    The neuron strongly activates on numeric and decimal sequences (e.g. phone‐number fragments, extensions, or other multi‐digit tokens).

    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
    よかった
    0.54
    \":
    0.54
    ෝ
    0.51
    ：「
    0.50
    තා
    0.50
    $-$
    0.50
    рое
    0.50
     \]
    0.50
    は何
    0.49
     হয়
    0.49
    POSITIVE LOGITS
    @
    3.30
     @
    2.97
    ]@
    2.11
    ＠
    2.08
     @_
    2.06
    \@
    2.00
    @(
    1.91
    }@
    1.89
     "@
    1.88
     at
    1.88
    Activations Density 0.050%

    No Known Activations