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. 238
    Prev
    Next
    INDEX
    Explanations

    silent film

    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
     mínima
    -0.86
    houettes
    -0.85
     Reeve
    -0.84
    că
    -0.84
     reality
    -0.84
     lingü
    -0.83
    entur
    -0.82
    Forza
    -0.81
    呪術
    -0.79
     to
    -0.79
    POSITIVE LOGITS
     Silent
    1.89
     silent
    1.80
    Silent
    1.71
    silent
    1.68
     silen
    1.43
     SIL
    1.40
     silently
    1.20
    SIL
    1.11
    Sil
    1.10
     Silence
    1.09
    Activations Density 0.011%

    No Known Activations