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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 18
    Prev
    Next
    INDEX
    Explanations

    forum discussion sections

    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
    艇
    -0.84
     at
    -0.84
    ้าง
    -0.83
     when
    -0.81
    engagent
    -0.77
    VARIABLE
    -0.76
     similar
    -0.76
     consistently
    -0.74
     Princesa
    -0.74
     сахара
    -0.73
    POSITIVE LOGITS
     forum
    1.52
    General
    1.41
     General
    1.38
    general
    1.35
     general
    1.31
     GENERAL
    1.23
    GENERAL
    1.21
     discussion
    1.19
     lounge
    1.15
    eneral
    1.13
    Activations Density 0.100%

    No Known Activations