© 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. 922
    Prev
    Next
    INDEX
    Explanations

    protected characteristic

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

    The neuron flags boilerplate legal/disclaimer language—especially forward-looking-statement and equal-opportunity/employment-opportunity passages.

    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
     exorbitant
    0.76
     grammaticality
    0.72
     まず
    0.70
    💴
    0.70
     бібліоте
    0.68
    Scientists
    0.67
     verkauft
    0.67
    Astronom
    0.67
    使う
    0.66
     شاعر
    0.66
    POSITIVE LOGITS
     pursuant
    0.55
     adversity
    0.54
    })$
    0.53
    will
    0.53
     performance
    0.51
    iston
    0.51
    we
    0.50
    is
    0.50
    areas
    0.49
    日々
    0.49
    Activations Density 0.015%

    No Known Activations