© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76558
    Prev
    Next
    INDEX
    Explanations

    'use strict'

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

    The neuron is triggering on code‐like tokens—especially numeric literals and programming keywords (e.g. “0”, “1”, “object”, “function”, “amd”).

    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
     recognizable
    -0.90
    няются
    -0.86
     recognition
    -0.85
    وية
    -0.82
     Spannung
    -0.79
     recognize
    -0.79
     organized
    -0.77
     financial
    -0.76
    appcompat
    -0.76
     excellence
    -0.74
    POSITIVE LOGITS
    ":
    1.35
    "+"
    1.20
    ”
    1.13
    ”-
    1.04
    "/
    1.03
    ",
    1.02
    ':
    1.02
    "-
    0.99
    ""
    0.96
    "
    0.96
    Activations Density 0.120%

    No Known Activations