© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 11082
    Prev
    Next
    INDEX
    Explanations

    must-visit

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

    The neuron detects words used in strong endorsements or recommendations (e.g. “must” or “worth”).

    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
    utilizzo
    1.22
    𝘴
    1.18
     bisschen
    1.12
    𝘸
    1.09
     굉장히
    1.08
    𝘵
    1.08
     Admittedly
    1.06
     Honestly
    1.05
    してる
    1.02
    cticamente
    1.02
    POSITIVE LOGITS
    1.27
    -
    1.18
     -
    1.04
    '
    1.02
     "
    0.97
    --
    0.96
       
    0.94
     .
    0.94
     during
    0.93
    .-
    0.92
    Activations Density 0.000%

    No Known Activations