© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 105191
    Prev
    Next
    INDEX
    Explanations

    I expressing self

    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
     about
    -2.19
    </em>
    -2.16
    $,
    -2.09
    ↵↵
    -1.98
     that
    -1.84
    、
    -1.82
     this
    -1.80
    }=\
    -1.77
     when
    -1.76
     孩子
    -1.76
    POSITIVE LOGITS
    perhaps
    1.72
     Departement
    1.67
     and
    1.63
     ABOVE
    1.61
    like
    1.60
    ’
    1.58
    âncias
    1.58
    鹟
    1.57
     devine
    1.57
     SOON
    1.57
    Activations Density 0.174%

    No Known Activations