© 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. 7089
    Prev
    Next
    INDEX
    Explanations

    quality of life

    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
     This
    -2.08
     mantend
    -1.88
    肪
    -1.81
     Then
    -1.80
    ilibrium
    -1.74
    StoryboardSegue
    -1.74
     How
    -1.73
     It
    -1.73
    但他
    -1.73
     Städten
    -1.71
    POSITIVE LOGITS
    .
    2.14
    e
    2.09
    even
    2.06
    0
    1.89
     connus
    1.84
    蔸
    1.74
    ’
    1.69
    )
    1.67
    ]
    1.67
     complet
    1.59
    Activations Density 0.019%

    No Known Activations