© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 103928
    Prev
    Next
    INDEX
    Explanations

    list, orders, harmful

    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
     Oaxaca
    -1.13
     Orkney
    -1.12
     oxygen
    -1.11
     ovaries
    -1.09
     ontology
    -1.09
     Otago
    -1.07
     Odisha
    -1.05
     orchestra
    -1.01
     Orissa
    -1.00
     Ordovician
    -0.99
    POSITIVE LOGITS
     меда
    0.84
     ambientes
    0.77
     воздухе
    0.75
     ApiResponse
    0.75
     Affiliations
    0.73
    ∩
    0.73
    mediaPlayer
    0.72
    沿革
    0.72
    奈川
    0.72
     интерьере
    0.72
    Activations Density 0.176%

    No Known Activations