© 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. 7191
    Prev
    Next
    INDEX
    Explanations

    together with others

    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
     same
    -1.66
     if
    -1.60
            
    -1.59
     there
    -1.55
     as
    -1.52
     in
    -1.48
    </h1>
    -1.46
     justifyContent
    -1.42
    이스
    -1.41
     is
    -1.38
    POSITIVE LOGITS
     Люди
    1.64
     they
    1.55
     破解
    1.52
     compétence
    1.47
    並且
    1.45
    そして
    1.42
    کیف
    1.41
     vozid
    1.41
     vya
    1.40
     兔
    1.40
    Activations Density 0.010%

    No Known Activations