© 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. 69257
    Prev
    Next
    INDEX
    Explanations

    by or to

    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
     it
    -1.81
     passenden
    -1.55
     would
    -1.55
     time
    -1.52
     originalen
    -1.46
    akhir
    -1.45
    utusan
    -1.43
     like
    -1.43
     arquitecto
    -1.41
     what
    -1.40
    POSITIVE LOGITS
    ddl
    1.52
    ang
    1.52
    eng
    1.44
    "]="
    1.43
    无论是
    1.34
     Atención
    1.34
    ries
    1.34
    ₃
    1.34
    ();
    1.33
    rom
    1.32
    Activations Density 0.001%

    No Known Activations