© 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. 3470
    Prev
    Next
    INDEX
    Explanations

    organization, decision, customer, column

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

    This neuron detects formal legal or policy wording (e.g., “disturbance,” “reserves the right to decide whether,” etc.).

    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
     сложных
    0.71
    それが
    0.67
    ことが
    0.66
     журнали
    0.66
    のだろう
    0.66
     conund
    0.66
     Александра
    0.65
    ˊ
    0.64
    指導
    0.64
     पुढ
    0.64
    POSITIVE LOGITS
     sikre
    0.82
    לות
    0.80
     parete
    0.77
    עים
    0.76
    ױ
    0.76
     tarafından
    0.75
     sejahtera
    0.75
     Nisan
    0.75
     nonzero
    0.74
    ılar
    0.74
    Activations Density 0.000%

    No Known Activations