© 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. 34-GEMMASCOPE-RES-131K
    7. 23523
    Prev
    Next
    INDEX
    Explanations

    head around

    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_34/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
    lineno
    -0.79
    隣
    -0.71
    рем
    -0.68
    ɐ
    -0.68
    淺
    -0.68
    ặp
    -0.67
    Collegamenti
    -0.67
    存于互联网档案馆
    -0.66
    jder
    -0.66
    getUsername
    -0.65
    POSITIVE LOGITS
     around
    8.81
    Around
    6.16
    around
    6.16
     Around
    5.72
     alrededor
    5.44
     autour
    5.22
     вокруг
    5.16
     AROUND
    4.97
    AROUND
    4.50
     حول
    4.22
    Activations Density 0.265%

    No Known Activations