© 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. 112719
    Prev
    Next
    INDEX
    Explanations

    plenty of

    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
     представителей
    -2.73
    嗫
    -2.55
    蓴
    -2.52
     operações
    -2.36
    籏
    -2.34
     realizando
    -2.33
    詎
    -2.33
    烀
    -2.31
    
    -2.31
    锨
    -2.30
    POSITIVE LOGITS
    ),
    2.72
     If
    2.53
    This
    2.52
    喲
    2.45
    нутрен
    2.41
     來
    2.36
    熒
    2.34
    吶
    2.34
    ).
    2.31
    唷
    2.31
    Activations Density 0.004%

    No Known Activations