© 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. 66167
    Prev
    Next
    INDEX
    Explanations

    not followed by attribute

    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
    齣
    -1.18
     некото
    -1.10
    iers
    -1.02
    ∉
    -1.02
     feveral
    -1.02
     firft
    -1.01
    呛
    -0.98
    tische
    -0.97
    浓郁
    -0.95
    dians
    -0.94
    POSITIVE LOGITS
     related
    1.52
     that
    1.45
     as
    1.39
     affiliated
    1.24
     like
    1.20
     connected
    1.20
     listed
    1.19
     my
    1.18
     officially
    1.16
     what
    1.12
    Activations Density 0.055%

    No Known Activations