© 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. 10-GEMMASCOPE-RES-131K
    7. 104394
    Prev
    Next
    INDEX
    Explanations

    lateinit var or how technology

    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_10/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
     to
    -2.33
    ’
    -2.28
    
    -2.17
    ྄
    -2.11
     largely
    -2.08
     dando
    -2.06
    熈
    -2.03
     fazendo
    -1.99
    }
    -1.95
     pertence
    -1.92
    POSITIVE LOGITS
    There
    2.63
    This
    2.28
    Since
    2.25
    s
    2.08
    The
    2.08
    Despite
    1.96
    Just
    1.95
    After
    1.95
    Still
    1.95
    Then
    1.93
    Activations Density 0.000%

    No Known Activations