© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71855
    Prev
    Next
    INDEX
    Explanations

    shifting position

    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_22/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
     on
    -1.02
     strengthen
    -1.01
     provide
    -0.98
     regarding
    -0.97
     focusing
    -0.93
    ļa
    -0.93
    环节
    -0.91
     τὴν
    -0.89
    靱
    -0.85
     or
    -0.85
    POSITIVE LOGITS
     réserver
    1.01
    <bos>
    0.92
     prostitu
    0.90
     tenth
    0.86
     unterschiedlich
    0.86
     mieli
    0.82
     fontFamily
    0.81
     asfal
    0.81
     interrom
    0.80
     obiettivi
    0.80
    Activations Density 0.182%

    No Known Activations