© 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. 1176
    Prev
    Next
    INDEX
    Explanations

    Hope that

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

    This neuron responds to verbs that invite or describe engaging in activities (e.g., coming, study, meet, relax) as part of a call-to-action.

    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
     मानक
    0.70
    に基づく
    0.70
    に基づ
    0.69
     Transparency
    0.66
    非常に
    0.65
    瞠
    0.65
     STANDARD
    0.64
     omfatt
    0.63
     aceptas
    0.61
     Posteriormente
    0.61
    POSITIVE LOGITS
     relaxing
    1.08
     relax
    1.07
     вечером
    1.03
     evenings
    1.00
    放松
    1.00
    relax
    0.99
    💤
    0.98
     relaxes
    0.97
    สบาย
    0.96
     reprieve
    0.95
    Activations Density 0.903%

    No Known Activations