© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 45301
    Prev
    Next
    INDEX
    Explanations

    North Bishop Avenue Historic District

    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_10/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
    Surprisingly
    -2.72
    Some
    -2.63
     був
    -2.56
    1
    -2.56
    quelize
    -2.55
    When
    -2.48
    Fär
    -2.38
    ⦊
    -2.34
     для
    -2.33
    These
    -2.31
    POSITIVE LOGITS
    埽
    2.69
    
    2.55
    蓠
    2.48
     he
    2.42
    ſam
    2.38
     rezer
    2.36
    箧
    2.23
     nahil
    2.19
     druga
    2.19
    たと
    2.19
    Activations Density 0.000%

    No Known Activations