© 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. 9550
    Prev
    Next
    INDEX
    Explanations

    parts of words, prefixes, suffixes

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

    This neuron fires on rare or out-of-vocabulary tokens—chiefly unusual proper names or other low-frequency 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
    ó
    0.15
    ਸ
    0.14
    ᴀ
    0.14
    ِل
    0.14
    َل
    0.13
    We
    0.13
    َه
    0.13
    ullie
    0.13
    ologne
    0.13
    ↵
    0.13
    POSITIVE LOGITS
     HBC
    0.16
     Mandalorian
    0.16
     RBD
    0.16
     ocas
    0.16
     maniera
    0.16
    getPage
    0.16
     Roles
    0.15
     Modo
    0.15
     Wayback
    0.15
     Twilight
    0.15
    Activations Density 0.002%

    No Known Activations