© 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. 129307
    Prev
    Next
    INDEX
    Explanations

    code delimiters and structure

    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
     climá
    -1.09
     Français
    -1.05
     grundsätzlich
    -1.04
     generell
    -1.01
     häufiger
    -0.99
     desmotiv
    -0.98
    шла
    -0.98
    Merhaba
    -0.95
     allmäh
    -0.95
    чня
    -0.94
    POSITIVE LOGITS
     anything
    1.35
    :+:
    1.06
     everything
    1.04
    tagHelper
    1.01
    </thead>
    0.98
     because
    0.98
     their
    0.94
    řevě
    0.93
     everyone
    0.93
     not
    0.90
    Activations Density 0.029%

    No Known Activations