© 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. 44013
    Prev
    Next
    INDEX
    Explanations

    encouraging

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

    This neuron detects occurrences of the word “encourage” (and its inflected forms).

    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
     we
    -2.23
    Ｑ
    -1.98
     a
    -1.98
    𖣘
    -1.88
    ＂
    -1.84
    ｣
    -1.80
    アニメ
    -1.80
     profundo
    -1.78
    ｢
    -1.78
     políticos
    -1.77
    POSITIVE LOGITS
     gleiche
    1.80
    ,”
    1.67
    ;
    1.66
    ogens
    1.66
    }$,
    1.63
    者が
    1.61
    </i>
    1.61
    );
    1.58
    }}+\
    1.57
    翅
    1.56
    Activations Density 0.015%

    No Known Activations