© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10219
    Prev
    Next
    INDEX
    Explanations

    scale and scalability

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

    The neuron detects occurrences of the root “scal” – i.e. words like scale, scaled, scalable, or scaling.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Paz
    0.62
    lai
    0.62
    czą
    0.59
    CAN
    0.58
    प
    0.58
    lte
    0.58
     Enzyme
    0.57
    κε
    0.55
    い
    0.54
    lc
    0.52
    POSITIVE LOGITS
     Scale
    1.49
     scales
    1.46
    scales
    1.44
     scale
    1.43
    Scal
    1.41
     escala
    1.41
     Scales
    1.41
     scal
    1.38
    scale
    1.35
    Scale
    1.32
    Activations Density 0.145%

    No Known Activations