© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 48105
    Prev
    Next
    INDEX
    Explanations

    technical descriptions and numbers

    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_34/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
     just
    -1.16
     on
    -1.12
     or
    -1.03
    What
    -1.00
     What
    -0.98
     by
    -0.97
     only
    -0.97
     what
    -0.94
     would
    -0.92
    There
    -0.92
    POSITIVE LOGITS
     dilapidated
    1.03
     Cura
    0.98
     rega
    0.96
     commerces
    0.94
     saveurs
    0.93
     offres
    0.93
    ândia
    0.90
     tâ
    0.89
     recipro
    0.89
    ],
    0.89
    Activations Density 0.009%

    No Known Activations