© 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. 22-GEMMASCOPE-RES-131K
    7. 15872
    Prev
    Next
    INDEX
    Explanations

    numbers followed by plus

    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_22/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
    鼯
    -1.57
     betreffende
    -1.52
    狆
    -1.34
    簓
    -1.34
     deklar
    -1.34
     抠
    -1.32
     komer
    -1.30
    ⎔
    -1.30
     testen
    -1.30
     ilumin
    -1.28
    POSITIVE LOGITS
     of
    2.05
    These
    1.88
    This
    1.87
    r
    1.75
    You
    1.60
    When
    1.59
    However
    1.56
    v
    1.51
    If
    1.51
    After
    1.48
    Activations Density 0.008%

    No Known Activations