© 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. 19532
    Prev
    Next
    INDEX
    Explanations

    github urls and project names

    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
     โ
    -1.53
     same
    -1.51
    着头
    -1.46
     senhora
    -1.43
    をしています
    -1.38
    ところが
    -1.38
    しようと
    -1.38
    🡺
    -1.37
     dichos
    -1.37
    -
    -1.35
    POSITIVE LOGITS
     of
    2.02
     Wartawan
    1.59
    ↵
    1.46
    henswürdigkeiten
    1.45
    既然
    1.44
    bundet
    1.43
    」，
    1.41
    Cevap
    1.40
     এবং
    1.40
     verdient
    1.35
    Activations Density 0.036%

    No Known Activations