© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118622
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     because
    -1.32
     with
    -1.20
     when
    -1.14
     now
    -1.03
     this
    -1.02
     undoubtedly
    -1.01
     considerable
    -1.01
     seems
    -1.00
     presumably
    -0.98
     does
    -0.95
    POSITIVE LOGITS
     jovem
    0.98
     gruesome
    0.96
    lly
    0.94
     overarching
    0.93
    connected
    0.93
    wanted
    0.93
    ś
    0.93
    maximum
    0.93
    abou
    0.93
    possibly
    0.92
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.