© 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. 22-GEMMASCOPE-RES-131K
    7. 15734
    Prev
    Next
    INDEX
    Explanations

    list item, more context

    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_22/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
    だよね
    -1.09
    seattle
    -0.90
    vmware
    -0.87
    Andrey
    -0.87
     limpieza
    -0.86
    diva
    -0.86
    áne
    -0.85
    }]
    -0.82
     Gleichzeitig
    -0.82
     Zudem
    -0.82
    POSITIVE LOGITS
    ƚ
    0.97
    rentino
    0.96
     αὐ
    0.81
    âce
    0.81
     lupa
    0.80
    engine
    0.80
     заня
    0.79
    ⊄
    0.79
    ordinates
    0.79
    のだろう
    0.78
    Activations Density 0.059%

    No Known Activations