© 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. 71489
    Prev
    Next
    INDEX
    Explanations

    usando JS

    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
    8
    -3.88
    9
    -3.77
    3
    -3.75
    4
    -3.56
    1
    -3.34
    </strong>
    -3.23
    5
    -3.14
    2
    -3.11
    D
    -3.11
    With
    -3.06
    POSITIVE LOGITS
    ☫
    3.27
    龊
    2.89
    开的
    2.78
    聍
    2.70
    诹
    2.70
    ࿊
    2.52
    踽
    2.52
    鹄
    2.41
    賒
    2.38
     罐
    2.34
    Activations Density 0.004%

    No Known Activations