© 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. 10-GEMMASCOPE-RES-131K
    7. 60174
    Prev
    Next
    INDEX
    Explanations

    build scripts and commands

    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
    ,”
    -3.17
    ’,
    -2.28
    ’
    -2.27
    ”
    -2.23
    “,
    -2.19
    ‘‘
    -2.19
     (“
    -2.17
    </u>
    -2.14
    “…
    -2.14
    ஂ
    -2.05
    POSITIVE LOGITS
    </h2>
    2.86
    </em>
    2.14
     decidiu
    2.09
    ühner
    2.05
     recebeu
    2.02
     pediu
    2.02
     "
    1.98
     are
    1.98
     soñar
    1.97
     abriu
    1.88
    Activations Density 0.145%

    No Known Activations