© 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. 108548
    Prev
    Next
    INDEX
    Explanations

    flip and flop

    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
    apt
    -0.82
     العين
    -0.75
    suk
    -0.74
     leicht
    -0.72
    s
    -0.71
     transmissão
    -0.71
    etal
    -0.70
     streets
    -0.69
    hei
    -0.68
    庙
    -0.68
    POSITIVE LOGITS
     Flip
    1.88
     flips
    1.77
     Fli
    1.77
     flip
    1.72
    Flip
    1.63
    flip
    1.63
     flipping
    1.59
     flop
    1.55
     flops
    1.48
    FLIP
    1.48
    Activations Density 0.009%

    No Known Activations