© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11485
    Prev
    Next
    INDEX
    Explanations

    advice and how-to guides

    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_22/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
     there
    -1.21
     all
    -1.09
     Affaires
    -1.06
    ("-");
    -1.02
     necessidade
    -1.02
    楽しかった
    -1.00
    ませて
    -1.00
     mediados
    -0.99
     этими
    -0.98
    取締役
    -0.98
    POSITIVE LOGITS
     how
    2.05
    如何
    1.95
     ways
    1.46
    去
    1.21
     Umgang
    1.21
    不要
    1.20
    怎么
    1.19
    tipps
    1.18
    虽然
    1.17
    Avoid
    1.14
    Activations Density 0.049%

    No Known Activations