© 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. 34-GEMMASCOPE-RES-131K
    7. 49089
    Prev
    Next
    INDEX
    Explanations

    programming examples or technical terms

    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_34/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
     выглядит
    -1.00
     teilweise
    -0.93
     основном
    -0.85
     or
    -0.84
     believes
    -0.82
     when
    -0.82
    幸いです
    -0.82
    ૌ
    -0.81
     famous
    -0.79
    伝わ
    -0.79
    POSITIVE LOGITS
     sonder
    1.13
    Alike
    1.05
     resultat
    1.05
     жан
    1.02
     solamente
    1.02
     sapatos
    1.00
     Tamanho
    1.00
     listeners
    1.00
     experimente
    0.99
     blau
    0.98
    Activations Density 0.027%

    No Known Activations