© 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. 13349
    Prev
    Next
    INDEX
    Explanations

    code delimiters and lists

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

    The neuron selectively activates on code identifiers—especially parameter and variable names (e.g. self, order, age, t, Name, fields).

    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
    }}{
    0.65
    }}{{
    0.55
    }]{
    0.55
    }:=
    0.54
     }{\
    0.53
    เก่า
    0.52
     }{
    0.50
    /}{
    0.50
    }{-
    0.50
    ]}{
    0.50
    POSITIVE LOGITS
    :
    1.19
     :
    0.88
    ：
    0.88
    ঃ
    0.86
    ︰
    0.75
    :@
    0.70
    ː
    0.66
    :'
    0.66
    :</
    0.66
     ؟
    0.65
    Activations Density 0.001%

    No Known Activations