© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 11818
    Prev
    Next
    INDEX
    Explanations

    support and solidarity

    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
    mira
    -0.85
     счастья
    -0.81
    説
    -0.79
    øren
    -0.79
    melin
    -0.79
    atase
    -0.78
    ṓ
    -0.77
     Erkrankungen
    -0.76
    łoży
    -0.76
    rex
    -0.75
    POSITIVE LOGITS
     solidarity
    5.13
     Solidarity
    3.61
    solid
    3.39
    Solid
    3.13
     solidarité
    3.08
     solidaridad
    3.02
     solidar
    2.97
     solidari
    2.92
     solid
    2.84
     SOLID
    2.83
    Activations Density 0.029%

    No Known Activations