© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67353
    Prev
    Next
    INDEX
    Explanations

    possibly or perhaps

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

    The neuron activates on the hedge/adverb “maybe,” i.e. tokens expressing uncertainty.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    },
    -2.34
     Strukt
    -2.11
    ate
    -2.06
    a
    -2.05
    </td>
    -2.02
     etui
    -2.00
    </tr>
    -1.91
    kelijk
    -1.90
    ية
    -1.84
    s
    -1.83
    POSITIVE LOGITS
    ↵
    2.44
    ка
    1.91
     “
    1.89
    <bos>
    1.80
    Pand
    1.64
     Bestandteil
    1.59
    ጵ
    1.57
    뎅
    1.57
    Possibly
    1.56
     able
    1.53
    Activations Density 0.004%

    No Known Activations