© 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. 14565
    Prev
    Next
    INDEX
    Explanations

    research

    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
    鲞
    -2.58
     was
    -2.53
    甃
    -2.45
    鬭
    -2.42
    ’
    -2.36
    ৢ
    -2.31
     keď
    -2.16
    近期
    -2.02
     stressing
    -2.00
     are
    -1.96
    POSITIVE LOGITS
     vollständ
    2.81
    .
    2.73
     erection
    2.45
    a
    2.38
    no
    2.30
    弍
    2.23
    ⸰
    2.22
    
    2.08
     レスト
    2.06
    ượ
    2.05
    Activations Density 0.029%

    No Known Activations