© 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. 25927
    Prev
    Next
    INDEX
    Explanations

    Hall of Fame inductions

    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
     respon
    -1.31
     >
    -1.21
     \\
    -1.20
     $
    -1.18
     That
    -1.16
     provides
    -1.14
     /*
    -1.10
    ansvar
    -1.10
    """
    -1.10
     \
    -1.10
    POSITIVE LOGITS
     years
    1.42
     atlet
    1.32
     ortop
    1.30
    💠
    1.30
     keramik
    1.29
     adil
    1.28
     reale
    1.27
     anún
    1.26
     registre
    1.25
     kapsul
    1.25
    Activations Density 0.018%

    No Known Activations