© 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. 77747
    Prev
    Next
    INDEX
    Explanations

    references and citations

    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
     Nedir
    -0.85
     giving
    -0.81
    ними
    -0.80
    ә
    -0.78
    UNICIP
    -0.78
     undeniably
    -0.77
    ṡ
    -0.77
    hema
    -0.76
    Cousin
    -0.76
     deeply
    -0.75
    POSITIVE LOGITS
     hongos
    1.00
     подтвер
    0.93
    needs
    0.92
    pending
    0.91
    ciation
    0.89
    throughout
    0.88
     pozost
    0.88
     Holistic
    0.84
     nové
    0.83
     gesprochen
    0.82
    Activations Density 0.014%

    No Known Activations