© 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. 6318
    Prev
    Next
    INDEX
    Explanations

    Transformer architecture

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

    This neuron strongly activates on tokens that are part of specific named entities or titles (e.g. book, film, recipe, or story 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
    s
    0.41
    oretically
    0.39
    सै
    0.36
    க்கொண்டு
    0.36
     framebuffer
    0.36
     tumours
    0.35
    ol
    0.34
    -
    0.34
    microphone
    0.34
    و
    0.34
    POSITIVE LOGITS
     Biblia
    0.46
     Relig
    0.44
     Religions
    0.44
    '।
    0.44
     Reputation
    0.43
     ポリエステル
    0.43
     Revised
    0.42
     Ünivers
    0.42
     Основ
    0.42
     学校
    0.42
    Activations Density 0.003%

    No Known Activations