© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91310
    Prev
    Next
    INDEX
    Explanations

    Feynman Elastic String

    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
    ಂಡ
    -0.75
    ʳ
    -0.68
    ('[
    -0.68
    Alli
    -0.68
    bertson
    -0.67
    zak
    -0.66
    rants
    -0.66
    Sarah
    -0.65
     $('.
    -0.64
     Raúl
    -0.64
    POSITIVE LOGITS
    Население
    0.84
     Nineteen
    0.82
     tính
    0.76
    注文
    0.72
    nó
    0.68
     Elena
    0.68
    mPaint
    0.67
     typeof
    0.66
    Nay
    0.66
    吹
    0.66
    Activations Density 0.579%

    No Known Activations