© 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. 92737
    Prev
    Next
    INDEX
    Explanations

    almost instantly

    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
     now
    -0.81
    ➐
    -0.79
     GestureDetector
    -0.79
    ffc
    -0.77
    jpeg
    -0.77
    anmoins
    -0.77
    вало
    -0.76
     your
    -0.76
    optional
    -0.75
     gesehen
    -0.75
    POSITIVE LOGITS
     almost
    4.69
    almost
    4.09
    Almost
    3.77
     Almost
    3.53
     quase
    3.25
    几乎
    3.23
     почти
    3.20
     casi
    3.05
     presque
    3.00
     hampir
    2.98
    Activations Density 0.071%

    No Known Activations