© 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. 128806
    Prev
    Next
    INDEX
    Explanations

    seating areas and spaces

    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
    Surprisingly
    -2.70
    There
    -2.48
    Having
    -2.44
    They
    -2.41
    It
    -2.38
    Since
    -2.38
    Because
    -2.34
    From
    -2.27
    After
    -2.27
     praktis
    -2.23
    POSITIVE LOGITS
     einheit
    2.56
    ).
    2.42
    絝
    2.41
    擼
    2.38
     ).
    2.30
    ࿚
    2.27
    栝
    2.27
     ),
    2.23
     histó
    2.22
     tainted
    2.22
    Activations Density 0.001%

    No Known Activations