© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31740
    Prev
    Next
    INDEX
    Explanations

    allow unknown sources

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

    The neuron fires on numeric tokens (any standalone numbers) in the text.

    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
     each
    -0.86
     ayrıca
    -0.80
    Logged
    -0.80
     pistes
    -0.79
    avait
    -0.79
     einzel
    -0.79
     opty
    -0.79
     facilidad
    -0.77
    專業
    -0.76
    ReactDOM
    -0.76
    POSITIVE LOGITS
     Unknown
    1.41
     Allow
    1.12
    Unknown
    1.11
     unknown
    1.09
     unk
    1.06
    允许
    1.04
    Allow
    1.02
    security
    1.01
     Security
    0.99
    permission
    0.96
    Activations Density 0.005%

    No Known Activations