© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 393
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on technical namespace or path identifiers—strings that look like code package names or URL/file path segments (e.g. dot- or slash-separated module or domain names).

    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
     จาก
    0.29
    Deze
    0.29
    From
    0.27
     이런
    0.26
     这个
    0.26
    Durch
    0.26
    ÉE
    0.26
    Ę
    0.25
    MONT
    0.25
     डेंगू
    0.25
    POSITIVE LOGITS
     utils
    0.19
     suas
    0.19
     config
    0.18
     düzenlenen
    0.18
     sebuah
    0.17
    ಗಳನ್ನು
    0.17
     său
    0.17
    стики
    0.17
     mediator
    0.17
     swoich
    0.17
    Activations Density 0.015%

    No Known Activations