© 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. 5530
    Prev
    Next
    INDEX
    Explanations

    also

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

    This neuron responds to instructional or promotional statements directed at the reader (e.g. “you can,” “we’ll,” “you’ll”)—signaling guidance, offers, or tutorial‐style language.

    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
     highly
    0.77
    _
    0.70
    Firstly
    0.67
     Öncelikle
    0.64
     まず
    0.60
     人気
    0.60
    ष्
    0.60
    FirstName
    0.59
    unächst
    0.59
    )$:
    0.59
    POSITIVE LOGITS
     also
    4.78
     também
    4.47
    also
    4.47
     también
    4.44
     также
    4.44
     також
    4.28
     myös
    4.22
     també
    4.09
    Also
    4.06
     Also
    4.03
    Activations Density 2.593%

    No Known Activations