© 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. 21080
    Prev
    Next
    INDEX
    Explanations

    buying things

    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
    ’
    -3.28
    “
    -3.14
    n
    -2.92
     they
    -2.75
     “
    -2.73
     примерно
    -2.73
     –
    -2.69
    ens
    -2.61
    ↵
    -2.56
    </em>
    -2.55
    POSITIVE LOGITS
    
    3.08
    鉭
    3.06
    􀂃
    2.89
     maniere
    2.88
     perpé
    2.88
    鐒
    2.81
     icône
    2.80
     mené
    2.78
    ſelves
    2.75
    𓁹
    2.75
    Activations Density 0.021%

    No Known Activations