© 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. 53804
    Prev
    Next
    INDEX
    Explanations

    booting sequences

    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
     outlines
    -0.88
    ars
    -0.86
    ッポン
    -0.84
    zel
    -0.84
    AGO
    -0.82
     durante
    -0.81
     близ
    -0.80
    ガジン
    -0.80
     besitzt
    -0.79
     ouvert
    -0.79
    POSITIVE LOGITS
     sequence
    1.24
     from
    1.18
     up
    1.17
     Sequence
    1.08
    sequence
    1.05
     normally
    1.02
     with
    0.93
     and
    0.93
     SEQUENCE
    0.89
    vorg
    0.87
    Activations Density 0.029%

    No Known Activations