© 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. 22-GEMMASCOPE-RES-131K
    7. 72358
    Prev
    Next
    INDEX
    Explanations

    HTML structural elements

    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
     that
    -1.34
     That
    -1.20
     which
    -1.19
     It
    -1.18
    prehensive
    -1.13
     its
    -1.12
    感じが
    -0.98
    って何
    -0.98
    mohon
    -0.97
     quindi
    -0.96
    POSITIVE LOGITS
    líben
    1.06
    もちゃ
    1.05
    ✳
    1.00
     リア
    0.98
    animity
    0.96
    SceneManagement
    0.96
     их
    0.96
    ҙ
    0.94
     発送
    0.93
     grotte
    0.92
    Activations Density 0.002%

    No Known Activations