© 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. 31-GEMMASCOPE-2-RES-16K
    7. 12426
    Prev
    Next
    INDEX
    Explanations

    starts sentences

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

    The neuron fires on section or heading titles—i.e. on tokens that mark the start of a new topical subsection or proper‐name header.

    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_31_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
     있어요
    0.88
     Deshalb
    0.88
    ᆢ
    0.86
     soooo
    0.86
    😊
    0.83
    喎
    0.83
     sooo
    0.82
    呀
    0.81
     quelquefois
    0.81
    :-)
    0.81
    POSITIVE LOGITS
     entirety
    0.96
    Whilst
    0.95
     debido
    0.87
     recieved
    0.87
     ██
    0.86
     whilst
    0.85
     جبکہ
    0.85
    Due
    0.84
    Alongside
    0.84
     estremamente
    0.84
    Activations Density 0.224%

    No Known Activations