© 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. 33668
    Prev
    Next
    INDEX
    Explanations

    conjunctions and additions

    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
    }=$
    -0.96
     agrico
    -0.93
    回戦
    -0.82
     işte
    -0.82
     pylint
    -0.82
     Souha
    -0.79
    現貨
    -0.79
     Fortunately
    -0.79
    metingen
    -0.79
    Somehow
    -0.78
    POSITIVE LOGITS
     also
    2.61
     plus
    2.20
     Plus
    2.14
     außerdem
    1.99
    Plus
    1.88
     Además
    1.86
     inoltre
    1.84
     además
    1.83
     Außerdem
    1.80
    plus
    1.77
    Activations Density 0.041%

    No Known Activations