© 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. 2685
    Prev
    Next
    INDEX
    Explanations

    total area

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

    The neuron activates on standalone numeric tokens (e.g. census figures, area values)—i.e. it detects 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
     in
    -1.02
     typically
    -0.96
     four
    -0.96
     more
    -0.91
     five
    -0.90
     two
    -0.89
     like
    -0.88
     entirely
    -0.88
     commonly
    -0.88
     choice
    -0.87
    POSITIVE LOGITS
    跳转
    1.13
     Jump
    1.11
     JUMP
    1.06
     跳转
    1.05
     Jumping
    1.04
     Jumps
    1.03
    jump
    1.02
     jump
    1.02
    XtraEditors
    1.01
     leaping
    1.01
    Activations Density 0.001%

    No Known Activations