© 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. 5964
    Prev
    Next
    INDEX
    Explanations

    telugu language Hell

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

    The main thing this neuron does is find numeric tokens containing decimal points (floating‐point numbers).

    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
    ประเทศไทย
    0.88
     българ
    0.88
     भारतात
    0.87
    日本では
    0.85
     일본
    0.84
    中国的
    0.83
     대한민국
    0.82
     ελλην
    0.82
     우리나라
    0.82
    ไทย
    0.81
    POSITIVE LOGITS
     GmbH
    0.85
     Selatan
    0.79
    orsz
    0.74
     Ltd
    0.72
     Pty
    0.70
    ®,
    0.69
    ,
    0.68
     LLC
    0.66
     لكرة
    0.66
    ",
    0.65
    Activations Density 0.281%

    No Known Activations