© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116369
    Prev
    Next
    INDEX
    Explanations

    public class

    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
     zatím
    -0.85
    Violin
    -0.84
     pediu
    -0.82
     disponibilità
    -0.82
    安い
    -0.80
     Tribun
    -0.80
     explicou
    -0.79
     debía
    -0.79
    Valores
    -0.79
     insol
    -0.78
    POSITIVE LOGITS
    ISTA
    0.88
    Canadian
    0.85
     drei
    0.85
    şen
    0.85
     akan
    0.85
     dva
    0.84
    Jeremy
    0.84
     Week
    0.82
    about
    0.82
    Calculate
    0.81
    Activations Density 0.010%

    No Known Activations