© 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. 10-GEMMASCOPE-RES-131K
    7. 86582
    Prev
    Next
    INDEX
    Explanations

    guess what

    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_10/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
    B
    -1.57
    0
    -1.43
    S
    -1.41
     discorso
    -1.36
    2
    -1.35
    V
    -1.34
    X
    -1.34
    p
    -1.32
    C
    -1.30
    K
    -1.27
    POSITIVE LOGITS
    
    1.43
     TIEMPO
    1.37
    umblr
    1.34
     regions
    1.34
    راهن
    1.33
     downloaden
    1.32
    ;%%
    1.31
    tiempo
    1.27
     mencionado
    1.27
     adicionar
    1.25
    Activations Density 0.035%

    No Known Activations