© 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. 66328
    Prev
    Next
    INDEX
    Explanations

    aka or other names, regions, or bases

    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
     immense
    -0.94
     fest
    -0.89
     Kombat
    -0.88
    ENOMEM
    -0.86
    <.
    -0.84
     
    -0.84
    bedded
    -0.84
    oted
    -0.84
    ordinate
    -0.83
    ocarditis
    -0.83
    POSITIVE LOGITS
    也就是
    1.02
     aka
    0.97
    <bos>
    0.89
    }]$
    0.86
    と呼ばれる
    0.85
     (=
    0.84
     AKA
    0.83
    СКИ
    0.82
    このような
    0.82
     will
    0.82
    Activations Density 0.106%

    No Known Activations