© 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. 92474
    Prev
    Next
    INDEX
    Explanations

    octopus URL definition

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

    This neuron activates on standalone numeric literals (tokens composed entirely of digits).

    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
     any
    -0.97
     at
    -0.86
    Teaser
    -0.78
     while
    -0.78
     during
    -0.74
    ToSend
    -0.70
     under
    -0.69
     go
    -0.69
     or
    -0.69
     un
    -0.69
    POSITIVE LOGITS
     input
    1.33
    INPUT
    1.26
    input
    1.25
    Input
    1.24
     INPUT
    1.22
     Input
    1.10
     instruction
    1.04
    inputs
    1.02
     instructions
    0.98
     Elves
    0.96
    Activations Density 0.009%

    No Known Activations