© 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. 7358
    Prev
    Next
    INDEX
    Explanations

    file path operations

    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
     –
    -2.72
    .
    -2.20
     of
    -2.13
    rozco
    -2.11
    –
    -2.00
    7
    -1.98
    ogeneity
    -1.89
    If
    -1.84
    titial
    -1.84
    0
    -1.83
    POSITIVE LOGITS
     delicada
    2.23
    <bos>
    2.17
     versátil
    2.02
     apetito
    1.95
     wichtigste
    1.91
     plenty
    1.91
     alivio
    1.91
    哢
    1.90
     your
    1.87
     recomendada
    1.87
    Activations Density 0.002%

    No Known Activations