© 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. 113088
    Prev
    Next
    INDEX
    Explanations

    lessons and experience

    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
     hodiny
    -1.62
     kabát
    -1.59
     derfor
    -1.52
     därför
    -1.36
     menangkap
    -1.35
    ovým
    -1.35
     Испании
    -1.34
     gått
    -1.33
     memperbaiki
    -1.32
     rám
    -1.31
    POSITIVE LOGITS
     of
    1.65
    s
    1.60
     with
    1.49
     across
    1.39
     successes
    1.38
    ta
    1.36
    u
    1.32
     electrica
    1.28
     which
    1.27
     グラン
    1.27
    Activations Density 0.040%

    No Known Activations