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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8625
    Prev
    Next
    INDEX
    Explanations

    telegraph key, my mum, depth of

    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
     chords
    -0.79
    readable
    -0.79
     eventdata
    -0.78
     readable
    -0.77
    ⚕
    -0.75
     croire
    -0.73
    Ⓛ
    -0.72
     Pascal
    -0.71
    VIDE
    -0.70
     ESTABL
    -0.69
    POSITIVE LOGITS
    Lumin
    0.91
     ZX
    0.88
     penulis
    0.82
     commonly
    0.82
     Benav
    0.81
    onPause
    0.80
     riguard
    0.75
     discussions
    0.75
     王子
    0.75
    Compartir
    0.73
    Activations Density 0.011%

    No Known Activations