© 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. 25439
    Prev
    Next
    INDEX
    Explanations

    successfully other files

    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
     někter
    -0.96
     szczególnie
    -0.90
    ecake
    -0.88
     nasled
    -0.84
     przede
    -0.83
     niektor
    -0.83
     häufig
    -0.82
    ɫ
    -0.82
     besonders
    -0.82
     bước
    -0.82
    POSITIVE LOGITS
    successfully
    1.25
     successful
    1.23
     successfully
    1.18
     успешно
    1.15
    successful
    1.14
    Successful
    1.10
    Successfully
    1.10
     other
    1.02
    正常
    1.02
    previously
    1.01
    Activations Density 0.329%

    No Known Activations