© 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. 6522
    Prev
    Next
    INDEX
    Explanations

    number combinations or rates

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

    This neuron fires on the very first “content” word that begins a new block or segment (i.e. the initial non‐stopword token at the start of a new paragraph or logical section).

    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
    ENIDO
    0.88
     преимущественно
    0.88
     единственный
    0.86
    缽
    0.86
     коэффициент
    0.82
     فوټبال
    0.82
    ผู้ชมในสนาม
    0.82
    Loksatta
    0.81
     लकार
    0.81
    REFLECTION
    0.80
    POSITIVE LOGITS
    ez
    0.77
    ate
    0.74
    ó
    0.73
     is
    0.71
    not
    0.71
     rivets
    0.70
    ov
    0.70
    iv
    0.68
    0.67
     or
    0.65
    Activations Density 0.001%

    No Known Activations