© 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. 71524
    Prev
    Next
    INDEX
    Explanations

    porosity and firing

    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
    y
    -3.39
    ’
    -3.20
    d
    -2.61
    ᠂
    -2.52
    ⬈
    -2.50
    the
    -2.45
    ate
    -2.45
    ation
    -2.45
    ].
    -2.41
    蠖
    -2.41
    POSITIVE LOGITS
     Their
    2.86
     THEIR
    2.69
     They
    2.52
    蕯
    2.47
    愎
    2.45
     emphas
    2.38
    幷
    2.33
    </td>
    2.27
     なお
    2.19
    莧
    2.19
    Activations Density 0.005%

    No Known Activations