© 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. 33479
    Prev
    Next
    INDEX
    Explanations

    listing, separating, quoting

    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
    ℮
    -0.91
    тили
    -0.85
     Kategor
    -0.82
     ADAPT
    -0.81
    ใช้งาน
    -0.81
    část
    -0.80
    ・「
    -0.80
    Ẩ
    -0.80
    atschapp
    -0.80
    ferred
    -0.79
    POSITIVE LOGITS
    分辨率
    0.96
    descend
    0.91
     alguno
    0.90
    bearded
    0.87
     viime
    0.86
     đạp
    0.84
     decisiones
    0.83
     aesthetic
    0.83
     decidiu
    0.83
     computadora
    0.82
    Activations Density 0.013%

    No Known Activations