© 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. 24-GEMMASCOPE-2-RES-16K
    7. 2239
    Prev
    Next
    INDEX
    Explanations

    code errors or limitations

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

    The neuron strongly activates on decimal‐number tokens (tokens representing 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_24_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
    cie
    0.83
    मु
    0.79
    프트
    0.75
     iniz
    0.73
     وعند
    0.73
    igas
    0.72
    πλ
    0.71
    ك
    0.71
    ci
    0.71
    queros
    0.71
    POSITIVE LOGITS
     casket
    0.88
     neonatal
    0.79
     voicemail
    0.77
     metamorphic
    0.77
    }[!
    0.77
    Externe
    0.77
    ？）
    0.76
    departments
    0.75
    department
    0.75
     sixties
    0.75
    Activations Density 0.000%

    No Known Activations