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. 8199
    Prev
    Next
    INDEX
    Explanations

    is followed by description

    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
    complished
    -1.12
    tifiable
    -1.09
    ølge
    -1.04
    valuable
    -1.00
     разнообраз
    -0.95
    isling
    -0.94
     APPROVED
    -0.91
    Filmografie
    -0.91
     consultato
    -0.88
     Fuerzas
    -0.88
    POSITIVE LOGITS
     also
    1.44
     designed
    1.38
     used
    1.38
     easy
    1.26
     very
    1.25
     equipped
    1.21
     suitable
    1.16
     able
    1.09
    総評
    1.05
     especially
    1.05
    Activations Density 0.006%

    No Known Activations