© 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. 10-GEMMASCOPE-RES-131K
    4. 3871
    Prev
    Next
    INDEX
    Explanations

    so/such followed by adjective

    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
     geprägt
    -1.56
    arqu
    -1.31
     genutzt
    -1.27
     когда
    -1.23
     beeintr
    -1.22
     sinnvoll
    -1.18
    が必要です
    -1.17
     gekennzeichnet
    -1.16
    When
    -1.14
     lorsque
    -1.14
    POSITIVE LOGITS
     ultimi
    1.19
     taky
    1.16
    ⇀
    1.12
    导致
    1.09
    )((
    1.06
    :+:
    1.05
     custos
    1.05
    ('/')
    1.05
    ///////////////
    1.05
     emphasis
    1.04
    Activations Density 0.031%

    No Known Activations