© 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. 13935
    Prev
    Next
    INDEX
    Explanations

    news, practice, business, policy, reading

    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
    צים
    -1.46
    biendo
    -1.45
     angen
    -1.39
     ſo
    -1.37
     теперь
    -1.37
    咘
    -1.34
    Unreal
    -1.34
     perioden
    -1.33
    iyle
    -1.29
     salomon
    -1.27
    POSITIVE LOGITS
     for
    1.84
    .”
    1.55
     most
    1.48
    }
    1.46
    utnant
    1.41
     When
    1.37
    //
    1.35
    ➴
    1.34
    \}\\
    1.32
    蚣
    1.32
    Activations Density 0.062%

    No Known Activations