© 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. 42123
    Prev
    Next
    INDEX
    Explanations

    limits and ranges of dates

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

    the mention of quantitative bounds or ranges (e.g. “limits,” “range,” “dates,” “hours”)

    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
    }{*}{}
    -1.49
    jącą
    -1.43
    anneer
    -1.43
     Económica
    -1.41
     estancias
    -1.38
     türlü
    -1.38
    chenen
    -1.36
    
    -1.36
    وافق
    -1.34
    </td>
    -1.33
    POSITIVE LOGITS
     –
    1.73
    e
    1.38
    ”.
    1.35
     sép
    1.34
     the
    1.34
    </strong>
    1.33
    -”
    1.27
    –
    1.23
     lakini
    1.23
     één
    1.23
    Activations Density 0.028%

    No Known Activations