© 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. 72283
    Prev
    Next
    INDEX
    Explanations

    code structure or syntax

    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
     this
    -1.33
     there
    -1.32
     you
    -1.31
     would
    -1.20
     that
    -1.20
     on
    -1.18
     people
    -1.12
     keep
    -1.11
     one
    -1.10
     while
    -1.08
    POSITIVE LOGITS
     applica
    1.16
     birçok
    1.05
     xan
    1.05
     espesor
    1.05
     usu
    1.05
     severa
    1.04
     delectable
    1.02
     resul
    1.02
     登山
    1.02
    Hvad
    1.01
    Activations Density 0.002%

    No Known Activations