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-3-1B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 116
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
      
    0.70
     disc
    0.69
     s
    0.67
     off
    0.66
     low
    0.63
     flat
    0.62
     e
    0.61
     "
    0.60
     per
    0.60
     single
    0.58
    POSITIVE LOGITS
    ibility
    1.29
    ifaiFace
    1.20
    ological
    1.20
    itive
    1.18
    ography
    1.10
    ative
    1.09
    ition
    1.08
    itative
    1.07
    ScriptBuf
    1.07
    ification
    1.06
    Activations Density 2.874%

    No Known Activations