© 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. 38461
    Prev
    Next
    INDEX
    Explanations

    compound words and phrases

    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
    uttgart
    -1.40
    懨
    -1.20
    🫕
    -1.19
    :+:
    -1.16
    ोड़
    -1.16
    Ирина
    -1.15
     любые
    -1.13
    킁
    -1.12
    ortment
    -1.12
    Wszyst
    -1.11
    POSITIVE LOGITS
     these
    1.55
     his
    1.35
     These
    1.32
     This
    1.22
     another
    1.21
     when
    1.20
     a
    1.18
    <h3>
    1.18
     after
    1.17
     this
    1.15
    Activations Density 0.157%

    No Known Activations