© 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. 1089
    Prev
    Next
    INDEX
    Explanations

    There's

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

    This neuron fires whenever an existential-style “there” introduces a clause (e.g. “there are…,” “there has been…,” “there was…”).

    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
    nya
    0.51
     progression
    0.48
    你在
    0.48
    И
    0.47
     straightforward
    0.45
    돼
    0.44
     skill
    0.44
     çöze
    0.44
    폐
    0.44
    ない
    0.43
    POSITIVE LOGITS
    简直
    0.59
    abouts
    0.58
    ੋ
    0.56
    ل
    0.54
    gleichen
    0.53
    jenigen
    0.50
    ائه
    0.50
     हैं
    0.49
    includes
    0.49
    のリ
    0.49
    Activations Density 0.115%

    No Known Activations