© 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. 59409
    Prev
    Next
    INDEX
    Explanations

    officials reporting or acting

    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
    蹰
    -2.70
    谘
    -2.44
     charismatic
    -2.44
    atação
    -2.42
     You
    -2.41
    rvats
    -2.41
    gebras
    -2.38
    证券
    -2.33
    讴
    -2.33
    闵
    -2.27
    POSITIVE LOGITS
    0
    3.53
    4
    3.23
    7
    3.13
    6
    3.02
    5
    2.94
    U
    2.84
    なんだか
    2.83
    部分が
    2.80
    1
    2.67
     stuks
    2.59
    Activations Density 0.004%

    No Known Activations