© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57110
    Prev
    Next
    INDEX
    Explanations

    sensory input or states

    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
    ھیے
    -0.98
     памяти
    -0.81
    tagez
    -0.78
    stě
    -0.78
     skupina
    -0.77
    арак
    -0.77
     также
    -0.77
     renowned
    -0.75
     边框
    -0.75
    aspectRatio
    -0.75
    POSITIVE LOGITS
     Seems
    0.95
     inexp
    0.89
    kiksi
    0.88
    似乎
    0.87
     something
    0.86
     seems
    0.86
     Somehow
    0.81
    Seems
    0.80
     scalp
    0.79
    Something
    0.78
    Activations Density 0.003%

    No Known Activations