© 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. 65047
    Prev
    Next
    INDEX
    Explanations

    CRC, hash, zone, IEP

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

    The neuron is strongly triggered by numeric literals and integer‐type specifiers (e.g. i8, i16, i32) in code.

    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
     marginLeft
    -1.05
     deras
    -0.88
     jejich
    -0.88
    Their
    -0.82
     deres
    -0.80
    🐒
    -0.76
     ihrer
    -0.76
    ariats
    -0.76
    cides
    -0.75
    msgSender
    -0.75
    POSITIVE LOGITS
     him
    0.84
    quise
    0.83
     things
    0.83
     Heft
    0.82
     bức
    0.82
     thing
    0.80
    淺
    0.80
     scur
    0.79
     everything
    0.77
     vindt
    0.77
    Activations Density 0.001%

    No Known Activations