© 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. 128588
    Prev
    Next
    INDEX
    Explanations

    loop indices and variable declarations

    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
    ECTOS
    -1.21
    honestly
    -1.09
     zwi
    -1.06
    glers
    -1.05
     kwal
    -1.02
     pn
    -1.02
     gier
    -1.01
    hā
    -0.99
    EEEEEE
    -0.98
     extravag
    -0.97
    POSITIVE LOGITS
     some
    1.30
     what
    1.26
     that
    1.17
     While
    1.16
     noteworthy
    1.10
     triliun
    1.06
     nearing
    1.06
     this
    1.04
     one
    1.03
     might
    1.02
    Activations Density 0.002%

    No Known Activations