© 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. 73088
    Prev
    Next
    INDEX
    Explanations

    names and headlines

    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
     two
    -1.20
     przechowy
    -1.07
     first
    -1.07
     this
    -1.06
     tillegg
    -1.06
    "
    -1.04
    }
    -1.03
    ospatial
    -1.02
    影片
    -1.02
    θηκε
    -1.02
    POSITIVE LOGITS
    ’
    1.29
     levering
    1.16
    ’).
    1.09
    referred
    1.06
     “(
    1.02
     mercurial
    1.01
    ,
    1.01
     VERY
    0.99
     “…
    0.98
    rinology
    0.96
    Activations Density 0.001%

    No Known Activations