© 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. 2935
    Prev
    Next
    INDEX
    Explanations

    Common but less likely

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

    This neuron detects subjective commentary or qualifiers—words expressing personal stance, intensifiers, or asides (e.g. “too,” “personally,” “issue,” “helpful,” “ignored”).

    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
    !!!!
    1.92
    !
    1.91
    !!!
    1.85
    !!
    1.79
    !!!!!!
    1.77
    !”
    1.76
    !!!!!
    1.76
    !’
    1.71
    !;
    1.71
    !!!!!!!
    1.68
    POSITIVE LOGITS
     Sorry
    0.82
     sorry
    0.80
     Guess
    0.76
     idk
    0.69
     honestly
    0.68
     Honestly
    0.68
     tbh
    0.66
    sorry
    0.65
     Maybe
    0.65
     Hmm
    0.62
    Activations Density 0.094%

    No Known Activations