© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 42135
    Prev
    Next
    INDEX
    Explanations

    burglar, lizard, food, month, Dr, James, welcome

    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
    檍
    -2.69
     ravi
    -2.66
    are
    -2.58
    跸
    -2.58
     ſame
    -2.56
     vokal
    -2.56
     disiplin
    -2.55
     maksi
    -2.50
     kado
    -2.44
     yetu
    -2.42
    POSITIVE LOGITS
    </h3>
    4.06
    </strong>
    2.91
     And
    2.77
    .
    2.75
     Also
    2.63
     Would
    2.61
     What
    2.59
     höheren
    2.53
     a
    2.50
     induce
    2.45
    Activations Density 0.000%

    No Known Activations