© 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. 31755
    Prev
    Next
    INDEX
    Explanations

    octopus URL

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

    The neuron primarily activates on numeric tokens or tokens containing digits (i.e. number literals).

    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
     Trotzdem
    -0.94
    PullParser
    -0.90
     konserv
    -0.90
    了一眼
    -0.88
     primar
    -0.87
     blessures
    -0.87
     prati
    -0.87
     akade
    -0.86
     fot
    -0.85
    urada
    -0.85
    POSITIVE LOGITS
     part
    1.12
     first
    0.99
     answer
    0.98
     removed
    0.92
     Part
    0.89
     program
    0.88
     solution
    0.87
     dangerous
    0.85
     who
    0.84
     all
    0.83
    Activations Density 0.004%

    No Known Activations