© 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. 10-GEMMASCOPE-RES-131K
    4. 684
    Prev
    Next
    INDEX
    Explanations

    New Zealand topics

    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
     kd
    -1.13
    ほんと
    -1.13
    continued
    -1.08
    そんなに
    -1.06
    ffling
    -1.03
    かもしれない
    -1.02
     Asus
    -1.02
     sts
    -1.01
    lada
    -1.00
    ほとん
    -1.00
    POSITIVE LOGITS
     when
    1.62
     but
    1.39
     these
    1.36
     it
    1.22
     will
    1.21
     at
    1.20
     right
    1.17
     through
    1.15
     during
    1.14
     frio
    1.11
    Activations Density 0.189%

    No Known Activations