© 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. 111318
    Prev
    Next
    INDEX
    Explanations

    phone numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    s
    -3.61
    which
    -3.27
    芣
    -2.72
    呖
    -2.67
     you
    -2.67
     was
    -2.64
    á
    -2.59
    ay
    -2.58
     doesn
    -2.56
    and
    -2.55
    POSITIVE LOGITS
     beinahe
    2.86
     varieties
    2.73
    
    2.67
    
    2.63
     praktischen
    2.55
    蕷
    2.53
     vorbere
    2.50
    襤
    2.44
    ㈰
    2.42
     gän
    2.41
    Activations Density 0.025%

    No Known Activations