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. 150
    Prev
    Next
    INDEX
    Explanations

    needle

    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
    Кре
    -0.71
    Hel
    -0.68
     Hel
    -0.68
    ıldığı
    -0.67
     junit
    -0.65
     증
    -0.65
    民国
    -0.64
     سعود
    -0.63
    shadowOpacity
    -0.63
    Tē
    -0.63
    POSITIVE LOGITS
     needle
    6.34
     needles
    5.44
    needle
    4.88
     Needle
    4.78
    Needle
    4.63
     Needles
    3.94
    針
    3.31
    针
    3.27
     aguja
    2.72
     agujas
    2.22
    Activations Density 0.060%

    No Known Activations