© 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. 14671
    Prev
    Next
    INDEX
    Explanations

    dialog

    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
    ⾒
    -2.89
     we
    -2.70
     manej
    -2.48
    訁
    -2.47
     fís
    -2.47
     estudi
    -2.44
     descub
    -2.39
    着手
    -2.39
    逦
    -2.38
    塤
    -2.38
    POSITIVE LOGITS
    }
    3.17
    \
    3.13
    ]
    2.94
    In
    2.81
    ."
    2.61
    “
    2.50
     क्योंकि
    2.47
    .
    2.47
    ”
    2.41
    說道
    2.39
    Activations Density 0.005%

    No Known Activations