© 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. 118908
    Prev
    Next
    INDEX
    Explanations

    driver mentions

    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
    n
    -1.29
     '
    -1.29
    s
    -1.27
    “
    -1.16
    M
    -1.16
    </em>
    -1.15
    R
    -1.11
     .
    -1.09
    ↵
    -1.08
    …
    -1.05
    POSITIVE LOGITS
     DRIVER
    1.63
     Driver
    1.41
     driver
    1.38
     Drivers
    1.32
     Indon
    1.23
     drivers
    1.22
    drivers
    1.21
    driver
    1.18
     klink
    1.15
    CURLOPT
    1.14
    Activations Density 0.014%

    No Known Activations