© 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. 22397
    Prev
    Next
    INDEX
    Explanations

    Eddystone or iBeacon terms

    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
    ”,
    -2.42
    ،
    -2.34
     которых
    -2.27
    栊
    -2.27
    },
    -2.27
     olympiques
    -2.25
    偌
    -2.22
    ات
    -2.20
    撓
    -2.20
     или
    -2.17
    POSITIVE LOGITS
    赑
    2.58
    );
    2.55
    sandalia
    2.50
    这件事
    2.36
     многие
    2.34
     
    2.33
    '
    2.33
    iſter
    2.19
    kurtka
    2.17
    u
    2.17
    Activations Density 0.003%

    No Known Activations