© 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. 22-GEMMASCOPE-RES-131K
    7. 15690
    Prev
    Next
    INDEX
    Explanations

    achievements and roles

    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
     they
    -1.13
     possuem
    -0.98
     posiad
    -0.90
    izzati
    -0.89
     They
    -0.86
    IllegalArgument
    -0.85
    anius
    -0.85
    瞌
    -0.84
     нашем
    -0.84
    highway
    -0.83
    POSITIVE LOGITS
     alongside
    1.81
     along
    1.79
     cùng
    1.63
    along
    1.59
     junto
    1.55
     вместе
    1.54
     gemeinsam
    1.43
    junto
    1.38
     bersama
    1.34
    和其他
    1.34
    Activations Density 0.060%

    No Known Activations