© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69253
    Prev
    Next
    INDEX
    Explanations

    celebrity news and gossip

    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
    \
    -1.56
    ";
    -1.54
     they
    -1.43
     $
    -1.43
     [...]
    -1.39
    ].
    -1.37
     หรือ
    -1.34
    ).
    -1.33
    ↵
    -1.31
    örung
    -1.31
    POSITIVE LOGITS
     trattano
    1.48
    ti
    1.45
     Dansk
    1.38
    搦
    1.36
     canin
    1.36
     reft
    1.36
    どのように
    1.35
    onka
    1.35
     fure
    1.34
    変わった
    1.34
    Activations Density 0.045%

    No Known Activations