© 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. 34-GEMMASCOPE-RES-131K
    7. 102492
    Prev
    Next
    INDEX
    Explanations

    code syntax and keywords

    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_34/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
     any
    -1.01
     may
    -0.80
     his
    -0.78
    ӑ
    -0.78
    ığını
    -0.78
    (&_
    -0.77
    positiva
    -0.76
     дерев
    -0.76
    YEAR
    -0.71
     $=
    -0.71
    POSITIVE LOGITS
     they
    1.41
     jejich
    1.16
     їх
    1.14
     Their
    1.09
     their
    1.06
     They
    1.06
    他們
    1.02
    They
    1.00
     их
    0.99
    Their
    0.95
    Activations Density 0.015%

    No Known Activations