© 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. 10-GEMMASCOPE-RES-131K
    7. 105962
    Prev
    Next
    INDEX
    Explanations

    all followed by another word

    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
     soluções
    -1.66
     incroy
    -1.57
     étr
    -1.55
    枼
    -1.55
     perigo
    -1.53
     esboço
    -1.53
     mettant
    -1.49
     soulign
    -1.49
    това
    -1.48
     clô
    -1.48
    POSITIVE LOGITS
     there
    1.61
     out
    1.58
     on
    1.57
    著名的
    1.43
     also
    1.41
    /");
    1.40
     determina
    1.38
    área
    1.38
     but
    1.35
     although
    1.33
    Activations Density 0.017%

    No Known Activations