© 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. 44850
    Prev
    Next
    INDEX
    Explanations

    Java class loading and reflection

    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
     silencioso
    -2.09
     montado
    -1.92
     estratégico
    -1.91
     animado
    -1.86
     aéreo
    -1.83
     cruzado
    -1.82
     robusto
    -1.80
     turístico
    -1.79
     climático
    -1.76
     controlado
    -1.75
    POSITIVE LOGITS
     disminu
    1.46
    0
    1.42
     in
    1.38
     NOT
    1.34
     //$
    1.34
     vengono
    1.29
    at
    1.24
     expulsion
    1.23
     attitudes
    1.21
    asına
    1.21
    Activations Density 0.001%

    No Known Activations