© 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. 59942
    Prev
    Next
    INDEX
    Explanations

    concepts followed by description

    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
     of
    -2.30
     in
    -1.53
    spyOn
    -1.45
    ”,
    -1.40
    ]],
    -1.34
     motyw
    -1.34
     from
    -1.34
    &=&
    -1.33
     összefoglaló
    -1.33
     схемы
    -1.32
    POSITIVE LOGITS
     some
    1.69
     that
    1.47
     später
    1.40
     where
    1.38
     estén
    1.38
     This
    1.34
     praktik
    1.34
     you
    1.31
    درب
    1.31
    Some
    1.29
    Activations Density 0.420%

    No Known Activations