© 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
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 1032
    Prev
    Next
    INDEX
    Explanations

    latex math notation

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

    This neuron activates on numeric tokens and number‐based strings (e.g. digits, decimal numbers, version or citation numbers, and regex quantifier patterns).

    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
     bienvenidos
    0.64
     específicamente
    0.61
    ”(
    0.61
    Biden
    0.58
    ⅞
    0.58
    %,
    0.58
    Medico
    0.58
    ⅝
    0.58
     baile
    0.57
    ⠀⠀⠀⠀
    0.57
    POSITIVE LOGITS
    _{\
    0.83
     }
    0.82
    .}
    0.82
    ')}
    0.81
    )}
    0.79
    -}
    0.78
    }
    0.78
     renormalized
    0.76
    }}
    0.73
    }}}
    0.72
    Activations Density 0.004%

    No Known Activations