© 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. 22-GEMMASCOPE-RES-131K
    7. 129673
    Prev
    Next
    INDEX
    Explanations

    states leading to outcomes

    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
     apsau
    -0.99
     contribuer
    -0.99
     poate
    -0.94
    bores
    -0.92
     första
    -0.90
     største
    -0.89
    msch
    -0.88
    öfe
    -0.88
     Cowboys
    -0.87
     \'
    -0.87
    POSITIVE LOGITS
     from
    1.13
     for
    1.10
     bym
    0.94
    Ventajas
    0.91
     way
    0.89
    ICALLY
    0.89
    Calidad
    0.89
     at
    0.88
     against
    0.88
     diretor
    0.86
    Activations Density 0.117%

    No Known Activations