© 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. 66986
    Prev
    Next
    INDEX
    Explanations

    asking how to do things

    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
    他们的
    -1.54
    Хотя
    -1.53
    他們的
    -1.53
    Даже
    -1.43
     gouverneur
    -1.43
     mêmes
    -1.41
    𓁹
    -1.39
     також
    -1.38
    or
    -1.38
     peintre
    -1.38
    POSITIVE LOGITS
    omenclature
    1.45
     onPause
    1.40
     We
    1.40
     it
    1.39
    }`);
    1.38
     which
    1.38
    ähkö
    1.37
    甴
    1.36
    riors
    1.36
     else
    1.36
    Activations Density 0.003%

    No Known Activations