© 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. 22-GEMMASCOPE-RES-131K
    7. 104729
    Prev
    Next
    INDEX
    Explanations

    32-bit and 64-bit quantities

    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_22/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
     nasze
    -1.27
    会的
    -1.18
    の時に
    -1.15
     hébergement
    -1.14
     людей
    -1.14
     louer
    -1.13
    lussen
    -1.13
     Wszyst
    -1.12
    毙
    -1.10
    ኗ
    -1.09
    POSITIVE LOGITS
    遑
    1.36
    現在は
    1.19
    tualmente
    1.08
     psicologia
    1.08
    公路
    1.06
     серь
    1.05
    vedad
    1.05
    但是在
    1.03
    (
    1.03
     vägen
    1.02
    Activations Density 0.017%

    No Known Activations