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. 8434
    Prev
    Next
    INDEX
    Explanations

    suggesting possibilities or actions

    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
    ⽅
    -0.91
    ShouldBe
    -0.90
    会被
    -0.89
    愷
    -0.89
     auttaa
    -0.89
     any
    -0.88
     být
    -0.87
     shouldBe
    -0.87
    '&:
    -0.87
    รู้สึก
    -0.83
    POSITIVE LOGITS
     use
    1.63
    用
    1.14
     storing
    1.09
     implement
    1.07
    使用
    1.06
     checks
    1.05
     store
    1.05
     uses
    1.03
     check
    1.02
    判断
    1.01
    Activations Density 0.667%

    No Known Activations