© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109873
    Prev
    Next
    INDEX
    Explanations

    start or end of time

    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
    continuing
    -1.24
     Projektu
    -1.22
     kimdir
    -1.18
     début
    -1.16
    beginning
    -1.13
    throughout
    -1.10
     insiste
    -1.08
     débuts
    -1.07
    槩
    -1.05
     leren
    -1.04
    POSITIVE LOGITS
     first
    1.39
     second
    1.22
     when
    1.22
     month
    1.20
     year
    1.09
     this
    1.09
     their
    1.08
     fourth
    1.08
     experiment
    1.05
     journey
    1.04
    Activations Density 0.047%

    No Known Activations