© 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. 34-GEMMASCOPE-RES-131K
    7. 31842
    Prev
    Next
    INDEX
    Explanations

    lists and dates

    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
     kommunik
    -0.84
    selen
    -0.81
    лений
    -0.79
     Comunicação
    -0.79
    zywa
    -0.77
     ſo
    -0.77
    ilig
    -0.76
    Mutagenicity
    -0.76
    batterie
    -0.76
    uruh
    -0.76
    POSITIVE LOGITS
    ][
    0.86
    tiker
    0.83
    ━━━
    0.82
    mergeFrom
    0.81
    ândia
    0.80
    ábamos
    0.79
    ITECH
    0.79
    PerformLayout
    0.79
    [\
    0.78
     item
    0.78
    Activations Density 0.000%

    No Known Activations