© 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. 64736
    Prev
    Next
    INDEX
    Explanations

    atomic and simple descriptions

    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
    niska
    -0.81
    pée
    -0.78
     설정
    -0.70
     culprit
    -0.69
     ví
    -0.68
    exams
    -0.68
     ストア
    -0.67
    Orc
    -0.66
     peony
    -0.65
    Tablet
    -0.64
    POSITIVE LOGITS
     atoms
    1.32
     atom
    1.20
     Atoms
    1.16
     MOT
    1.13
     atomic
    1.10
     Atomic
    1.09
     vapor
    1.06
    Rb
    1.05
    atoms
    1.05
     alkali
    1.04
    Activations Density 0.036%

    No Known Activations