© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 68160
    Prev
    Next
    INDEX
    Explanations

    words indicating cause or relation

    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
     キー
    -1.59
     verschied
    -1.47
     will
    -1.47
     distintas
    -1.44
    最後の
    -1.42
    ፅ
    -1.39
     which
    -1.36
    岀
    -1.34
     they
    -1.34
    áme
    -1.34
    POSITIVE LOGITS
     and
    2.52
    Ayrıca
    1.65
    ان
    1.65
     flesta
    1.60
     a
    1.52
    ＆
    1.39
    Özel
    1.32
    Gemeinde
    1.32
    руппа
    1.32
     an
    1.30
    Activations Density 0.199%

    No Known Activations