© 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. 93014
    Prev
    Next
    INDEX
    Explanations

    act of shrinking

    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
    脆弱
    -0.85
    celled
    -0.85
    juma
    -0.84
    RectangleBorder
    -0.84
    ryan
    -0.83
    richlet
    -0.83
    careous
    -0.82
    kkar
    -0.82
    igus
    -0.81
     chlorine
    -0.80
    POSITIVE LOGITS
    shrink
    1.80
    Shrink
    1.77
     shrink
    1.77
     Shrink
    1.63
     shrinking
    1.41
    缩
    1.41
     shrinks
    1.38
     shrunk
    1.37
     Shr
    1.36
     shrinkage
    1.33
    Activations Density 0.016%

    No Known Activations