© 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. 71009
    Prev
    Next
    INDEX
    Explanations

    major common categories

    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
    aneity
    -1.27
    や
    -1.24
     a
    -1.23
     to
    -1.14
    ктей
    -1.13
    teness
    -1.13
    itans
    -1.09
    рым
    -1.09
    phere
    -1.08
    などを
    -1.08
    POSITIVE LOGITS
     conocidas
    1.22
     acestui
    1.16
     known
    1.16
    ใหญ
    1.16
     such
    1.14
     acestei
    1.10
     préférable
    1.07
    tahui
    1.06
     inapropiados
    1.05
     wyłą
    1.05
    Activations Density 0.068%

    No Known Activations