© 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. 22-GEMMASCOPE-RES-131K
    7. 39510
    Prev
    Next
    INDEX
    Explanations

    absence of something

    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_22/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
    zka
    -0.93
    totta
    -0.87
     üzerinde
    -0.85
     gefertigt
    -0.85
    création
    -0.84
     from
    -0.83
    tojas
    -0.83
    잘
    -0.82
    运用
    -0.82
    raits
    -0.82
    POSITIVE LOGITS
     or
    1.27
     yet
    1.13
    而是
    1.02
     sondern
    0.95
     nor
    0.94
     Yet
    0.88
     geometrical
    0.88
     hujan
    0.85
     anymore
    0.83
     или
    0.81
    Activations Density 0.122%

    No Known Activations