© 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. 1421
    Prev
    Next
    INDEX
    Explanations

    point differential

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

    The neuron is activated by numeric tokens, especially multi‐digit numbers representing statistics, counts, or other quantitative data.

    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
    fbe
    -0.84
     Freunden
    -0.82
     simpli
    -0.81
     гг
    -0.81
     on
    -0.77
     stimulation
    -0.73
    hept
    -0.72
     induction
    -0.70
     escala
    -0.70
     Iowa
    -0.69
    POSITIVE LOGITS
    Differential
    1.14
     differential
    1.06
    差
    0.99
     goal
    0.98
    goal
    0.95
     Differential
    0.94
     differentials
    0.93
     commento
    0.93
    GF
    0.92
     Inferior
    0.92
    Activations Density 0.010%

    No Known Activations