© 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. 32316
    Prev
    Next
    INDEX
    Explanations

    package.json file contents

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

    The neuron is responding to numeric tokens (digits and number‐like strings) and related metadata separators (e.g. the ‘|’ used in YAML frontmatter).

    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
     terrific
    -0.80
    Directories
    -0.76
     Poco
    -0.75
    amata
    -0.74
     Giant
    -0.73
     Fifteen
    -0.71
    και
    -0.71
    <0x8D>
    -0.70
     WON
    -0.69
     Seventeen
    -0.69
    POSITIVE LOGITS
     Nonlinear
    0.79
    ByName
    0.79
     Verkehrs
    0.73
     nonlinear
    0.72
     twelve
    0.72
     detention
    0.67
    ၈
    0.67
    Nonlinear
    0.66
    واز
    0.64
    Wim
    0.64
    Activations Density 0.415%

    No Known Activations