© 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. 36393
    Prev
    Next
    INDEX
    Explanations

    attention

    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
    雳
    -2.61
    N
    -2.38
     большим
    -2.17
    ⟐
    -2.16
    M
    -2.05
     若
    -2.05
    er
    -1.94
    훌
    -1.93
    бурга
    -1.92
     تمامی
    -1.92
    POSITIVE LOGITS
    .
    2.81
     که
    2.42
    that
    2.42
     bahwa
    2.31
    </h4>
    2.31
     That
    2.30
     THAT
    2.27
    ஂ
    2.27
    n
    2.23
     ``
    2.22
    Activations Density 0.013%

    No Known Activations