© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129716
    Prev
    Next
    INDEX
    Explanations

    writ of mandamus or habeas corpus

    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
    Thankyou
    -1.12
     achet
    -0.99
     éte
    -0.96
    sı
    -0.94
    ironically
    -0.93
     Dernière
    -0.92
    ladesh
    -0.89
     jeudi
    -0.88
    Danke
    -0.88
    demás
    -0.86
    POSITIVE LOGITS
     rarely
    1.21
     الوزراء
    1.19
     cases
    1.14
     remedy
    1.12
     extraordinary
    1.12
     exceptional
    1.12
    ēc
    1.10
     excepcional
    1.05
     seldom
    1.05
     prieš
    1.04
    Activations Density 0.024%

    No Known Activations