© 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. 25916
    Prev
    Next
    INDEX
    Explanations

    questions and labels

    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
     Although
    -1.39
    Although
    -1.20
     or
    -1.14
     if
    -1.13
     unparalleled
    -1.12
    它们的
    -1.08
     undeniably
    -1.04
     If
    -1.03
     antiquated
    -1.02
    دید
    -1.01
    POSITIVE LOGITS
     և
    1.36
     largely
    1.34
    ：
    1.30
     kinda
    1.25
     matters
    1.18
     focuses
    1.17
     into
    1.16
     señalar
    1.16
    ›
    1.15
     adalah
    1.14
    Activations Density 0.010%

    No Known Activations