© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 40003
    Prev
    Next
    INDEX
    Explanations

    web url paths and routing

    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
    ומרים
    -1.13
     plafon
    -1.05
     siena
    -1.05
     libere
    -1.03
     restant
    -1.00
     enorme
    -0.99
     refroid
    -0.98
     monstrous
    -0.96
     Gesund
    -0.96
     warszawa
    -0.96
    POSITIVE LOGITS
     on
    1.34
     for
    1.24
     their
    1.20
     if
    1.20
    href
    1.19
     at
    1.15
    بدأ
    1.12
     where
    1.09
     without
    0.99
     website
    0.98
    Activations Density 0.013%

    No Known Activations