© 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. 34-GEMMASCOPE-RES-131K
    7. 110903
    Prev
    Next
    INDEX
    Explanations

    Stronger Than That

    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_34/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
     divertida
    -1.45
     рік
    -1.45
    менять
    -1.44
    ﱠ
    -1.43
     cómoda
    -1.40
    Ď
    -1.40
     стъ
    -1.35
    toDouble
    -1.30
     musíte
    -1.30
    AddWithValue
    -1.26
    POSITIVE LOGITS
    though
    1.58
    although
    1.50
    这是一
    1.38
    tions
    1.38
    ⤒
    1.37
    Transk
    1.36
     dugaan
    1.35
     aboli
    1.34
     detecta
    1.33
    Տես
    1.33
    Activations Density 0.462%

    No Known Activations