© 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. 2713
    Prev
    Next
    INDEX
    Explanations

    shift operations

    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
     změ
    -0.76
    antaine
    -0.73
    ⊹
    -0.72
     udaler
    -0.71
    句話
    -0.71
    нительно
    -0.70
     externo
    -0.70
     운
    -0.70
    nych
    -0.69
    offsetHeight
    -0.68
    POSITIVE LOGITS
     shift
    2.44
    Shift
    2.25
     Shift
    2.19
    shift
    2.17
     shifting
    2.09
     shifts
    2.08
     Shifting
    2.00
     SHIFT
    1.88
    shifting
    1.87
     shifted
    1.84
    Activations Density 0.025%

    No Known Activations