© 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. 22-GEMMASCOPE-RES-131K
    4. 67322
    Prev
    Next
    INDEX
    Explanations

    is followed by adjectives or past participles

    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
     மற்றும்
    -1.46
     también
    -1.38
    感じです
    -1.36
    												
    -1.36
     különböző
    -1.30
     and
    -1.30
    Удачи
    -1.28
     myös
    -1.25
    }.
    -1.23
     depresión
    -1.22
    POSITIVE LOGITS
     to
    2.17
     in
    1.52
     by
    1.39
     again
    1.31
    岁的
    1.19
     with
    1.18
     outono
    1.16
     for
    1.13
     now
    1.13
    ·
    1.10
    Activations Density 0.022%

    No Known Activations