© 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. 6984
    Prev
    Next
    INDEX
    Explanations

    hello, data, kes followed by punctuation

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

    The neuron is detecting embedded file names or file‐path references (i.e. tokens that are parts of filenames or URLs with extensions).

    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
    ).—
    0.75
     ".")
    0.66
    ;*/
    0.65
     بنائیں
    0.65
    !;
    0.65
     toer
    0.61
     ।,
    0.60
    "+"|".
    0.57
    సారి
    0.56
     '.')
    0.56
    POSITIVE LOGITS
    .
    1.33
    _.
    1.02
    。
    0.95
    *.
    0.95
    ++.
    0.87
    _
    0.84
    __.
    0.81
    _{
    0.80
    +.
    0.76
    ™.
    0.75
    Activations Density 0.090%

    No Known Activations