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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32161
    Prev
    Next
    INDEX
    Explanations

    object hash code

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires whenever text refers to object hash codes (e.g. “hashes,” “hashCode”) in code or discussion.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     Duisburg
    -0.89
    댓글
    -0.83
    COL
    -0.82
     જ
    -0.78
    endswith
    -0.78
    setCellValue
    -0.77
    Cleaning
    -0.75
    GRAY
    -0.73
     tegas
    -0.73
    kmale
    -0.69
    POSITIVE LOGITS
     hashCode
    2.25
     hash
    2.19
    hashCode
    2.08
    HashCode
    1.90
     Hash
    1.74
    hash
    1.71
    GetHashCode
    1.70
    HASH
    1.51
     hashing
    1.41
    Hash
    1.38
    Activations Density 0.011%

    No Known Activations