© 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
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7552
    Prev
    Next
    INDEX
    Explanations

    `for` `in` `range`

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

    The neuron strongly activates on occurrences of the token “in.”

    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
    =[]
    0.73
    Vector
    0.69
    Len
    0.64
    nilai
    0.64
    Rem
    0.63
    int
    0.62
    LoginActivity
    0.62
    j
    0.62
    для
    0.62
    /=
    0.60
    POSITIVE LOGITS
     range
    0.94
     xrange
    0.79
     tqdm
    0.76
     RANGE
    0.70
     रेंज
    0.68
     ranged
    0.67
     Range
    0.66
     reversed
    0.65
     enumerate
    0.64
    になると
    0.64
    Activations Density 0.001%

    No Known Activations