© 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. 34-GEMMASCOPE-RES-131K
    7. 63489
    Prev
    Next
    INDEX
    Explanations

    multilingual technical descriptions

    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
     herself
    -1.59
    herself
    -1.02
    \
    -0.96
     her
    -0.85
     his
    -0.85
     hoi
    -0.81
     welcher
    -0.79
    把他
    -0.79
     who
    -0.78
    少了
    -0.78
    POSITIVE LOGITS
     которое
    2.80
     welches
    1.88
     яке
    1.80
     koje
    1.40
     its
    1.40
     које
    1.30
     které
    1.28
     ktoré
    1.13
    вание
    1.10
    čko
    1.09
    Activations Density 0.015%

    No Known Activations