© 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. 26089
    Prev
    Next
    INDEX
    Explanations

    alternative options

    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
     outback
    -0.89
     ftate
    -0.87
     подтвер
    -0.86
     beweisen
    -0.85
     firft
    -0.85
    💃
    -0.85
     AMAZ
    -0.84
    オリ
    -0.82
     میکنم
    -0.81
     Hra
    -0.81
    POSITIVE LOGITS
     alternatives
    1.14
     alternative
    1.10
     via
    1.00
     options
    0.94
    uguetes
    0.94
    还可以
    0.93
     alternativa
    0.92
    enziale
    0.92
     Alternatively
    0.92
     online
    0.89
    Activations Density 0.110%

    No Known Activations