© 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. 22435
    Prev
    Next
    INDEX
    Explanations

    in

    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
    0
    -2.92
    to
    -2.89
    1
    -2.78
    8
    -2.59
    We
    -2.48
    6
    -2.44
    u
    -2.38
    7
    -2.38
    3
    -2.33
    </td>
    -2.30
    POSITIVE LOGITS
    </strong>
    2.78
    </h1>
    2.28
    蕻
    1.99
    ꜆
    1.95
     suo
    1.95
    鐡
    1.91
    を使った
    1.90
    StoryboardSegue
    1.88
    rabh
    1.84
     estuvo
    1.81
    Activations Density 0.081%

    No Known Activations