© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 129000
    Prev
    Next
    INDEX
    Explanations

    of [degree, order, type, simple, different, all, weight]

    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
    -1.75
     but
    -1.54
     and
    -1.42
     it
    -1.36
    )–
    -1.35
     being
    -1.34
    }+
    -1.33
    return
    -1.30
    }-
    -1.27
    after
    -1.26
    POSITIVE LOGITS
     حت
    1.52
     preocupado
    1.36
    ⚣
    1.35
     iniciado
    1.33
    tinggi
    1.33
     referido
    1.33
    îtra
    1.31
     enviado
    1.30
     segurando
    1.30
     arşivlendi
    1.29
    Activations Density 0.156%

    No Known Activations