© 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. 1697
    Prev
    Next
    INDEX
    Explanations

    over-, sub-, pre- prefixes

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

    The neuron detects common two‐letter English prefix substrings (especially “un-” and “re-”) at the start of words.

    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
    t
    1.06
     four
    0.97
    }
    0.97
     maar
    0.92
    ۴
    0.91
     →
    0.90
     ۴
    0.89
     vier
    0.88
    esque
    0.88
     वाले
    0.87
    POSITIVE LOGITS
    elevationMap
    0.88
    اد
    0.83
    𝘽
    0.83
    ਤੀ
    0.82
    trashItem
    0.81
    ț
    0.81
     पकड़
    0.80
     סי
    0.79
     আকৃষ্ট
    0.79
    ेक्षित
    0.78
    Activations Density 0.071%

    No Known Activations