© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 47834
    Prev
    Next
    INDEX
    Explanations

    numerical or quantified outcomes

    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
    Gabri
    -0.77
     problems
    -0.74
    ohl
    -0.73
     providing
    -0.72
     five
    -0.72
    álni
    -0.71
     after
    -0.70
    ianto
    -0.70
    OCT
    -0.69
     OCD
    -0.69
    POSITIVE LOGITS
    ”
    0.81
     Balak
    0.81
     Armor
    0.80
     Shou
    0.76
     dette
    0.76
    گیری
    0.74
    holds
    0.74
    blown
    0.73
     Armour
    0.73
     Lever
    0.73
    Activations Density 0.015%

    No Known Activations