© 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. 71185
    Prev
    Next
    INDEX
    Explanations

    numbers and programming code

    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
    chargez
    -1.10
    好
    -1.04
     الجمعة
    -0.96
     Cómo
    -0.89
    回来
    -0.89
     mystère
    -0.89
     of
    -0.88
    这些
    -0.87
     colección
    -0.87
    Reducer
    -0.86
    POSITIVE LOGITS
     zweite
    1.11
     and
    1.00
    jącej
    0.98
     others
    0.91
    ൈ
    0.89
    ところで
    0.88
    עים
    0.85
     други
    0.85
    ino
    0.84
    jącego
    0.84
    Activations Density 0.001%

    No Known Activations