Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7863
    Prev
    Next
    INDEX
    Explanations

    documentation sections and terms

    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
     when
    -1.00
     how
    -0.93
    BeforeAll
    -0.90
     this
    -0.86
     outset
    -0.81
     these
    -0.77
    addGroup
    -0.77
    工人
    -0.76
    __*/
    -0.76
    ână
    -0.76
    POSITIVE LOGITS
     BASKET
    0.90
     jorden
    0.80
     التع
    0.79
    θή
    0.79
     dét
    0.76
    ﻓ
    0.76
    tugas
    0.76
    continu
    0.75
     duran
    0.75
     erweiterten
    0.73
    Activations Density 0.004%

    No Known Activations