© 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. 10-GEMMASCOPE-RES-131K
    7. 128476
    Prev
    Next
    INDEX
    Explanations

    imagination

    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_10/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
    盌
    -2.61
    ра
    -2.36
    釹
    -2.31
    栻
    -2.20
    ר
    -2.20
    噥
    -2.20
    鄣
    -2.14
     Their
    -2.14
    ーーーー
    -2.11
    最早
    -2.09
    POSITIVE LOGITS
    .
    2.56
    a
    2.55
    ]
    2.47
    ?
    2.42
    {
    2.31
    }
    2.20
     “
    2.16
    d
    2.08
     tę
    1.98
    倣
    1.98
    Activations Density 0.004%

    No Known Activations