© 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. 110493
    Prev
    Next
    INDEX
    Explanations

    hash and array manipulations

    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
     λι
    -0.80
     copper
    -0.78
     cobre
    -0.77
    llong
    -0.77
     высоким
    -0.75
    Quinn
    -0.74
    ICAL
    -0.73
    Copper
    -0.73
     !=
    -0.71
    ")
    -0.71
    POSITIVE LOGITS
     hash
    3.92
    hash
    3.61
     Hash
    3.55
    Hash
    3.42
    HASH
    2.94
     HASH
    2.75
     hashes
    2.67
     hashing
    2.14
    HashMap
    2.05
     HashMap
    2.05
    Activations Density 0.073%

    No Known Activations