© 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. 58757
    Prev
    Next
    INDEX
    Explanations

    charges for defendants

    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
     drastically
    -0.83
     Midwest
    -0.82
    Ｗ
    -0.81
    lentes
    -0.80
    Patience
    -0.80
    Papel
    -0.77
    ósfera
    -0.74
     Initially
    -0.74
     Censo
    -0.74
     while
    -0.73
    POSITIVE LOGITS
     llenar
    1.02
    ひとり
    0.88
     episodios
    0.84
     retraso
    0.82
    awi
    0.81
     sensibilidad
    0.80
    에
    0.80
    瑆
    0.80
    nert
    0.79
     lectores
    0.79
    Activations Density 0.004%

    No Known Activations