© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103333
    Prev
    Next
    INDEX
    Explanations

    spring season

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

    The neuron activates strongly on the word “spring,” i.e. mentions of the season.

    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
     ‘
    -2.81
    }
    -2.70
    *
    -2.67
    </strong>
    -2.45
     you
    -2.38
    ↵
    -2.38
    <
    -2.36
    ?’
    -2.33
    リボン
    -2.27
    "../
    -2.27
    POSITIVE LOGITS
    婓
    2.84
    The
    2.78
    Ꮞ
    2.75
    庥
    2.66
    اسية
    2.56
     silvestre
    2.53
    酲
    2.53
    🦤
    2.50
    欵
    2.47
     bonita
    2.45
    Activations Density 0.013%

    No Known Activations