© 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. 71416
    Prev
    Next
    INDEX
    Explanations

    majoring in or major-general

    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
     nuestras
    -2.33
     amenaz
    -2.25
    ingtones
    -2.06
    dersfield
    -2.02
     posteriormente
    -2.02
     איך
    -1.99
    😦
    -1.98
     nossas
    -1.96
     使っ
    -1.95
     oficialmente
    -1.95
    POSITIVE LOGITS
    3
    2.55
    5
    2.28
    1
    2.27
    Y
    2.20
    6
    2.20
    Also
    2.17
    ﹍﹍
    2.16
    2
    2.13
    Is
    2.13
    and
    2.13
    Activations Density 0.006%

    No Known Activations