© 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
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 72
    Prev
    Next
    INDEX
    Explanations

    . The

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

    The neuron strongly activates on text about self‐worth and confidence—phrases where the author or audience is urged to believe in, prove, or question their own value.

    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
    ),
    0.50
    )،
    0.50
    ,
    0.46
    ),
    0.46
    )、
    0.46
    ӵ
    0.45
    (),
    0.45
    .),
    0.41
    ()),
    0.41
    ='',
    0.41
    POSITIVE LOGITS
     But
    0.97
     That
    0.93
     And
    0.91
     Who
    0.90
     What
    0.84
     Perhaps
    0.84
     It
    0.84
     Maybe
    0.82
     Nobody
    0.82
     Isn
    0.79
    Activations Density 2.269%

    No Known Activations