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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 1577
    Prev
    Next
    INDEX
    Explanations

    SHA-1, SHA-256, SHA-512

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

    The neuron detects mentions of cryptographic hash and signing algorithms (e.g. “SHA1,” “SHA256,” “HMAC,” “MD5,” “SCRAM,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     That
    -1.77
    ⁰
    -1.72
    whom
    -1.68
    髕
    -1.68
    inning
    -1.67
     ,
    
    -1.66
    
    -1.66
    /',
    -1.64
    xdc
    -1.61
    ± 
    -1.59
    POSITIVE LOGITS
    Ꮨ
    1.71
     sowohl
    1.66
    <bos>
    1.53
     präsentieren
    1.51
    \(^
    1.49
     delicately
    1.48
     delivering
    1.48
     plentiful
    1.45
     美食
    1.44
     labd
    1.43
    Activations Density 0.012%

    No Known Activations