© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7743
    Prev
    Next
    INDEX
    Explanations

    planning and decision making

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

    The neuron strongly lights up on tokens in advice‐ or instruction-giving contexts (e.g. “you,” “for,” “using,” “will,” “estimate”), i.e. it detects imperative/advisory 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
     hemic
    0.59
     molar
    0.57
     disertai
    0.57
    ૫
    0.55
     sekali
    0.55
    羟
    0.55
     thorough
    0.54
    狐
    0.54
     pent
    0.54
     biometric
    0.53
    POSITIVE LOGITS
     designing
    1.38
     planning
    1.30
    planning
    1.30
     Designing
    1.24
    Planning
    1.21
     deciding
    1.18
    Designing
    1.17
     Planning
    1.13
     selecting
    1.13
     Selecting
    1.13
    Activations Density 0.682%

    No Known Activations