© 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. 47464
    Prev
    Next
    INDEX
    Explanations

    triple digits, quadruple, multi-digit numbers

    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
     Donkey
    -0.74
    LineColor
    -0.72
    락
    -0.71
    Donkey
    -0.70
    UFACT
    -0.66
    ො
    -0.65
    นม
    -0.64
    ϸ
    -0.63
     malice
    -0.63
     fart
    -0.63
    POSITIVE LOGITS
     triple
    3.78
    triple
    3.20
    Triple
    2.81
     Triple
    2.61
     quadruple
    2.20
     triples
    2.00
    三位
    1.62
     трех
    1.58
    的三
    1.52
    three
    1.45
    Activations Density 0.044%

    No Known Activations