© 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-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 39303
    Prev
    Next
    INDEX
    Explanations

    from head to toe

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

    This neuron detects span/range expressions of the form “X to Y” or hyphenated X-to-Y (e.g. “head to toe,” “floor-to-ceiling,” “coast to coast”).

    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
    곽
    -1.31
     or
    -1.25
    </sub>
    -1.21
    或
    -1.20
     가져
    -1.20
     sasaran
    -1.19
    eafter
    -1.19
    `,
    -1.18
     тыс
    -1.18
    <b>
    -1.16
    POSITIVE LOGITS
     frumos
    1.44
     vechi
    1.41
     unul
    1.40
     acoper
    1.38
     noastre
    1.38
     echip
    1.38
     acestui
    1.34
     decât
    1.34
     prieten
    1.33
     asupra
    1.30
    Activations Density 0.045%

    No Known Activations