© 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. 12150
    Prev
    Next
    INDEX
    Explanations

    enables interpretation

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

    The neuron strongly fires on PHP runtime warning/error messages (e.g. “Use of undefined constant …” lines with file paths and line 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
    Gx
    0.55
     Recorder
    0.54
    ilab
    0.52
    DSS
    0.52
    िख
    0.52
     كار
    0.52
    ĥ
    0.52
    Dx
    0.51
    ℤ
    0.50
    conceptual
    0.49
    POSITIVE LOGITS
     Template
    1.23
     templates
    1.21
     Templates
    1.21
    Template
    1.20
    模板
    1.16
     template
    1.13
     templ
    1.12
    テンプレート
    1.09
    Templates
    1.08
     Templ
    1.07
    Activations Density 0.038%

    No Known Activations