© 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. 68283
    Prev
    Next
    INDEX
    Explanations

    need for

    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
     our
    -1.62
     slova
    -1.53
     sonriente
    -1.53
     all
    -1.48
     one
    -1.48
    zdro
    -1.37
     oryginal
    -1.36
    슘
    -1.35
     ακό
    -1.32
     sonriendo
    -1.31
    POSITIVE LOGITS
    </sup>
    2.02
    </h4>
    1.87
     in
    1.54
     다른
    1.41
     for
    1.36
    e
    1.34
     totiž
    1.34
     sekitar
    1.33
    </h2>
    1.32
     not
    1.30
    Activations Density 0.026%

    No Known Activations